Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/config.json +7 -8
- checkpoint-1000/model-00001-of-00003.safetensors +3 -0
- checkpoint-1000/model-00002-of-00003.safetensors +3 -0
- checkpoint-1000/model-00003-of-00003.safetensors +3 -0
- checkpoint-1000/model.safetensors.index.json +1020 -0
- checkpoint-1000/optimizer.pt +2 -2
- checkpoint-1000/rng_state.pth +1 -1
- checkpoint-1000/trainer_state.json +0 -0
- checkpoint-1000/training_args.bin +1 -1
- checkpoint-1500/config.json +7 -8
- checkpoint-1500/model-00001-of-00003.safetensors +3 -0
- checkpoint-1500/model-00002-of-00003.safetensors +3 -0
- checkpoint-1500/model-00003-of-00003.safetensors +3 -0
- checkpoint-1500/model.safetensors.index.json +1020 -0
- checkpoint-1500/optimizer.pt +2 -2
- checkpoint-1500/rng_state.pth +1 -1
- checkpoint-1500/trainer_state.json +0 -0
- checkpoint-1500/training_args.bin +1 -1
- checkpoint-2000/config.json +7 -8
- checkpoint-2000/model-00001-of-00003.safetensors +3 -0
- checkpoint-2000/model-00002-of-00003.safetensors +3 -0
- checkpoint-2000/model-00003-of-00003.safetensors +3 -0
- checkpoint-2000/model.safetensors.index.json +1020 -0
- checkpoint-2000/optimizer.pt +2 -2
- checkpoint-2000/rng_state.pth +1 -1
- checkpoint-2000/trainer_state.json +0 -0
- checkpoint-2000/training_args.bin +1 -1
- checkpoint-2500/config.json +7 -8
- checkpoint-2500/model-00001-of-00003.safetensors +3 -0
- checkpoint-2500/model-00002-of-00003.safetensors +3 -0
- checkpoint-2500/model-00003-of-00003.safetensors +3 -0
- checkpoint-2500/model.safetensors.index.json +1020 -0
- checkpoint-2500/optimizer.pt +2 -2
- checkpoint-2500/rng_state.pth +1 -1
- checkpoint-2500/trainer_state.json +0 -0
- checkpoint-2500/training_args.bin +1 -1
- checkpoint-2997/config.json +7 -8
- checkpoint-2997/model-00001-of-00003.safetensors +3 -0
- checkpoint-2997/model-00002-of-00003.safetensors +3 -0
- checkpoint-2997/model-00003-of-00003.safetensors +3 -0
- checkpoint-2997/model.safetensors.index.json +1020 -0
- checkpoint-2997/optimizer.pt +2 -2
- checkpoint-2997/rng_state.pth +1 -1
- checkpoint-2997/trainer_state.json +0 -0
- checkpoint-2997/training_args.bin +1 -1
- checkpoint-500/config.json +7 -8
- checkpoint-500/model-00001-of-00003.safetensors +3 -0
- checkpoint-500/model-00002-of-00003.safetensors +3 -0
- checkpoint-500/model-00003-of-00003.safetensors +3 -0
- checkpoint-500/model.safetensors.index.json +1020 -0
checkpoint-1000/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-1000/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1ade5256c1994ceaea57b36487da445ff5fa3bd970757a711a206a17f987862
|
| 3 |
+
size 4986088344
|
checkpoint-1000/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb1e5e8869c7c036006dfd2113a779bea5437d10e79f89b5a6d55131d7837c7
|
| 3 |
+
size 4985688360
|
checkpoint-1000/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7054eff5c598fbbfc10deda92eb600ff34fa89c1f5e7fbd0cefbd5fde9f96d7e
|
| 3 |
+
size 3407796744
|
checkpoint-1000/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|
checkpoint-1000/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d2238db343edcba72b8d16e24a2cbb9b4319dabd324b5461d1bcb717ff5ce8a
|
| 3 |
+
size 16695613
|
checkpoint-1000/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f998b81a7c9ec9576c1eb3934948ddc2e93559dcb8816f2c74465b567d39eeae
|
| 3 |
size 14244
|
checkpoint-1000/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae1000de8543fc66656e14e0874e31bd9110f9789b5d68e3afdc182cfa7e766
|
| 3 |
size 5240
|
checkpoint-1500/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-1500/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:524f1b2a3d487121b35e9413666471718655037ef32ea66ee7662de1dfe671a3
|
| 3 |
+
size 4986088344
|
checkpoint-1500/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61ed51810042b9ef0969b82467f35f3cea88f9d712136b7f22006b26a7f8d46e
|
| 3 |
+
size 4985688360
|
checkpoint-1500/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96c1468c8b1715d253c5a261e5cc744e06ed0c654f8bfaad28981b1349095126
|
| 3 |
+
size 3407796744
|
checkpoint-1500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|
checkpoint-1500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffc2d4bb97b961a20e7140ceae840fbc600e40e460ed74602abc561298dbd2eb
|
| 3 |
+
size 16695613
|
checkpoint-1500/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cae694e4dc4a229e80ef6dc1dd9a1cb2d63d2baac73d6b43e28fd9f1ae739fa7
|
| 3 |
size 14244
|
checkpoint-1500/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae1000de8543fc66656e14e0874e31bd9110f9789b5d68e3afdc182cfa7e766
|
| 3 |
size 5240
|
checkpoint-2000/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-2000/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a625f6f3b2f8893f71aa6dcd7e0fc4340c09252efc0e740fd48d0eaffcb816bd
|
| 3 |
+
size 4986088344
|
checkpoint-2000/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:557b61c559358454ed196c640f4a0d45ba06cc053a20ee05c2877bf9ecd06465
|
| 3 |
+
size 4985688360
|
checkpoint-2000/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4659500777218e1b14f90ce3e76468cfe931135e6e090800e202803b138961b
|
| 3 |
+
size 3407796744
|
checkpoint-2000/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|
checkpoint-2000/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef84b1ed891b67ba55a1f977bf286cc8244f02aa7867412cce968465ff2e7155
|
| 3 |
+
size 16695613
|
checkpoint-2000/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21899bd22f2a224a53f41656db06af1ff9e25bab84684440b6e87e56ee498088
|
| 3 |
size 14244
|
checkpoint-2000/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae1000de8543fc66656e14e0874e31bd9110f9789b5d68e3afdc182cfa7e766
|
| 3 |
size 5240
|
checkpoint-2500/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-2500/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c604a38042e22292fb9bfbf587f1ed9e8b00ce9ffb668a2069dc9550f45cdd2
|
| 3 |
+
size 4986088344
|
checkpoint-2500/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b2fb54898460088053df672aa349694182281b60c60c654f2bc0a572a87f864
|
| 3 |
+
size 4985688360
|
checkpoint-2500/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be1d528517bcaee1178e60c26105642e5e29029a3201355894fad7b2aaf57959
|
| 3 |
+
size 3407796744
|
checkpoint-2500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|
checkpoint-2500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3b90030d40004b67548c3e9f2d74560d5fdc38e42574eead175e101ee1b9613
|
| 3 |
+
size 16695613
|
checkpoint-2500/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a050cacc41c9e392abf1c66fff28f5182eb15091933f76c45b40ae0c90fa7c3
|
| 3 |
size 14244
|
checkpoint-2500/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae1000de8543fc66656e14e0874e31bd9110f9789b5d68e3afdc182cfa7e766
|
| 3 |
size 5240
|
checkpoint-2997/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-2997/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c369f48abbcd62a29748ea19ce35e34ebc1ad9122ed611d55ad8034aa3915a72
|
| 3 |
+
size 4986088344
|
checkpoint-2997/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51551c8055bc83d503c48a85e3b723a1498d3d9c07fb0699ce0cb2de8eaf7480
|
| 3 |
+
size 4985688360
|
checkpoint-2997/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ae91973f87c9a5cb7ffd3e1a35b0db4ef04262aba76c923e1a2550582678ee1
|
| 3 |
+
size 3407796744
|
checkpoint-2997/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|
checkpoint-2997/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47dab79becb582851cf1dd57a8ea06b445abb587a4bef61ad00261274d0c2c55
|
| 3 |
+
size 16695613
|
checkpoint-2997/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a64f34286243934087e7b7f69307e1c4ef2178683952385fa52b8a871013d0b
|
| 3 |
size 14244
|
checkpoint-2997/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2997/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae1000de8543fc66656e14e0874e31bd9110f9789b5d68e3afdc182cfa7e766
|
| 3 |
size 5240
|
checkpoint-500/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/nllb-200-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -7,27 +7,26 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"d_model":
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim":
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers":
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
-
"encoder_ffn_dim":
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
-
"encoder_layers":
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
-
"num_hidden_layers":
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
| 30 |
-
"tokenizer_class": "NllbTokenizer",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.42.4",
|
| 33 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/nllb-200-3.3B",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 0,
|
| 10 |
+
"d_model": 2048,
|
| 11 |
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 8192,
|
| 19 |
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 24,
|
| 21 |
"eos_token_id": 2,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
| 24 |
"max_length": 200,
|
| 25 |
"max_position_embeddings": 1024,
|
| 26 |
"model_type": "m2m_100",
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"scale_embedding": true,
|
|
|
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.42.4",
|
| 32 |
"use_cache": true,
|
checkpoint-500/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1322fc5e714165adc5003b78fb7a3e4d610003a87d65b681979016c1eed3bb19
|
| 3 |
+
size 4986088344
|
checkpoint-500/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab201ea7fa73e0a69d25af44197d5e4703dde7643fb8512088ab26e20e7c294
|
| 3 |
+
size 4985688360
|
checkpoint-500/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca63e9149d65cfd0366ae273ad0891d029a708f8a1e4ce7913e49ba09c136bab
|
| 3 |
+
size 3407796744
|
checkpoint-500/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1020 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13379452928
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 9 |
+
"model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 10 |
+
"model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 12 |
+
"model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 13 |
+
"model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 14 |
+
"model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 16 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 17 |
+
"model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 18 |
+
"model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 20 |
+
"model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
|
| 21 |
+
"model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 22 |
+
"model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 24 |
+
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 25 |
+
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 26 |
+
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 29 |
+
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 30 |
+
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 32 |
+
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 33 |
+
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 34 |
+
"model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 89 |
+
"model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 90 |
+
"model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 91 |
+
"model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 92 |
+
"model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 93 |
+
"model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 94 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 95 |
+
"model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 96 |
+
"model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
|
| 97 |
+
"model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
|
| 98 |
+
"model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
|
| 99 |
+
"model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
|
| 100 |
+
"model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 101 |
+
"model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 102 |
+
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 113 |
+
"model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 114 |
+
"model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 115 |
+
"model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 116 |
+
"model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
|
| 126 |
+
"model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 127 |
+
"model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 128 |
+
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 129 |
+
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 130 |
+
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 131 |
+
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 132 |
+
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 133 |
+
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 134 |
+
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 135 |
+
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 136 |
+
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 137 |
+
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 138 |
+
"model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 139 |
+
"model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 140 |
+
"model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 141 |
+
"model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 142 |
+
"model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 143 |
+
"model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
|
| 149 |
+
"model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
|
| 150 |
+
"model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
|
| 151 |
+
"model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
|
| 152 |
+
"model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
|
| 255 |
+
"model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 257 |
+
"model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 258 |
+
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 261 |
+
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 266 |
+
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 267 |
+
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 269 |
+
"model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 271 |
+
"model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 273 |
+
"model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 274 |
+
"model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 275 |
+
"model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 276 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 277 |
+
"model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 278 |
+
"model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
|
| 280 |
+
"model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
|
| 282 |
+
"model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 283 |
+
"model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 285 |
+
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 286 |
+
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 288 |
+
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 289 |
+
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 291 |
+
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 293 |
+
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 295 |
+
"model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 296 |
+
"model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 297 |
+
"model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 298 |
+
"model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 299 |
+
"model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 300 |
+
"model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 301 |
+
"model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 302 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 303 |
+
"model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 304 |
+
"model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
|
| 305 |
+
"model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
|
| 306 |
+
"model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
|
| 307 |
+
"model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
|
| 308 |
+
"model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 309 |
+
"model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 310 |
+
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 311 |
+
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 312 |
+
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 313 |
+
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 314 |
+
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 315 |
+
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 316 |
+
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 317 |
+
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 318 |
+
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 319 |
+
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 320 |
+
"model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 451 |
+
"model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 452 |
+
"model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 453 |
+
"model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
+
"model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 455 |
+
"model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 456 |
+
"model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 457 |
+
"model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 458 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 459 |
+
"model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 460 |
+
"model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
|
| 461 |
+
"model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 462 |
+
"model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
|
| 463 |
+
"model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 464 |
+
"model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 465 |
+
"model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
+
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 467 |
+
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 468 |
+
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 469 |
+
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 470 |
+
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 471 |
+
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 484 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 485 |
+
"model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 486 |
+
"model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
|
| 487 |
+
"model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 488 |
+
"model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
|
| 489 |
+
"model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 490 |
+
"model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 491 |
+
"model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
+
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 493 |
+
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 494 |
+
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 495 |
+
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 496 |
+
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 497 |
+
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 498 |
+
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 499 |
+
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 500 |
+
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 501 |
+
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 502 |
+
"model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 503 |
+
"model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 504 |
+
"model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 505 |
+
"model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 506 |
+
"model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 507 |
+
"model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 508 |
+
"model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 509 |
+
"model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
|
| 513 |
+
"model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 514 |
+
"model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 516 |
+
"model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 518 |
+
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 519 |
+
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 521 |
+
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 523 |
+
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 527 |
+
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 609 |
+
"model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 610 |
+
"model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 611 |
+
"model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 612 |
+
"model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 613 |
+
"model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 615 |
+
"model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 616 |
+
"model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
|
| 617 |
+
"model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 618 |
+
"model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
|
| 619 |
+
"model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 621 |
+
"model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
+
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 623 |
+
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
+
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 625 |
+
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 626 |
+
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 627 |
+
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 628 |
+
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 629 |
+
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
+
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 631 |
+
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 632 |
+
"model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 633 |
+
"model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 634 |
+
"model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
| 731 |
+
"model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
| 733 |
+
"model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
| 734 |
+
"model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 735 |
+
"model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 736 |
+
"model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
| 747 |
+
"model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 751 |
+
"model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 755 |
+
"model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 757 |
+
"model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 761 |
+
"model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
| 763 |
+
"model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 767 |
+
"model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 771 |
+
"model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 773 |
+
"model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 777 |
+
"model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
| 779 |
+
"model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 783 |
+
"model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 787 |
+
"model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 789 |
+
"model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 793 |
+
"model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
| 795 |
+
"model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 799 |
+
"model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 803 |
+
"model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 805 |
+
"model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 809 |
+
"model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
| 811 |
+
"model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 815 |
+
"model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 819 |
+
"model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 821 |
+
"model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 825 |
+
"model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
| 844 |
+
"model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
| 845 |
+
"model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
| 846 |
+
"model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 847 |
+
"model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 849 |
+
"model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 850 |
+
"model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 851 |
+
"model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 852 |
+
"model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 853 |
+
"model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 854 |
+
"model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 855 |
+
"model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 856 |
+
"model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 857 |
+
"model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 858 |
+
"model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
| 859 |
+
"model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
| 860 |
+
"model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
| 861 |
+
"model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
| 862 |
+
"model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 863 |
+
"model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 865 |
+
"model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 866 |
+
"model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 867 |
+
"model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 868 |
+
"model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 869 |
+
"model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 871 |
+
"model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 872 |
+
"model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 873 |
+
"model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 874 |
+
"model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
| 875 |
+
"model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
| 877 |
+
"model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
| 878 |
+
"model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 879 |
+
"model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 880 |
+
"model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 881 |
+
"model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 882 |
+
"model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 883 |
+
"model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 884 |
+
"model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 885 |
+
"model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 886 |
+
"model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 887 |
+
"model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 888 |
+
"model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 889 |
+
"model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 890 |
+
"model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
| 891 |
+
"model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
| 892 |
+
"model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
|
| 893 |
+
"model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
|
| 894 |
+
"model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 895 |
+
"model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 896 |
+
"model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
| 897 |
+
"model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 898 |
+
"model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
| 899 |
+
"model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 900 |
+
"model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
| 901 |
+
"model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 902 |
+
"model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
| 903 |
+
"model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 904 |
+
"model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 905 |
+
"model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 906 |
+
"model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
| 907 |
+
"model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
| 908 |
+
"model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
| 909 |
+
"model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
| 910 |
+
"model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 911 |
+
"model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 912 |
+
"model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 913 |
+
"model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 914 |
+
"model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 915 |
+
"model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 916 |
+
"model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 917 |
+
"model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 918 |
+
"model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 919 |
+
"model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 920 |
+
"model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 921 |
+
"model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 922 |
+
"model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
| 923 |
+
"model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
| 924 |
+
"model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
| 925 |
+
"model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
| 926 |
+
"model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 927 |
+
"model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 928 |
+
"model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 929 |
+
"model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 930 |
+
"model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 931 |
+
"model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 932 |
+
"model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 933 |
+
"model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 934 |
+
"model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 935 |
+
"model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 936 |
+
"model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 937 |
+
"model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 938 |
+
"model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
| 939 |
+
"model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
| 940 |
+
"model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
| 941 |
+
"model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
| 942 |
+
"model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 943 |
+
"model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 944 |
+
"model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 945 |
+
"model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 946 |
+
"model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 947 |
+
"model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 948 |
+
"model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 949 |
+
"model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 950 |
+
"model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 951 |
+
"model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 952 |
+
"model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 953 |
+
"model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 954 |
+
"model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
| 955 |
+
"model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 956 |
+
"model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
| 957 |
+
"model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 958 |
+
"model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 959 |
+
"model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 960 |
+
"model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 961 |
+
"model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 962 |
+
"model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 963 |
+
"model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 964 |
+
"model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 965 |
+
"model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 966 |
+
"model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 967 |
+
"model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 968 |
+
"model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 969 |
+
"model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 970 |
+
"model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
| 971 |
+
"model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 972 |
+
"model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
| 973 |
+
"model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 974 |
+
"model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 975 |
+
"model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 976 |
+
"model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 977 |
+
"model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 978 |
+
"model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 979 |
+
"model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 980 |
+
"model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 981 |
+
"model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 982 |
+
"model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 983 |
+
"model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 984 |
+
"model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 985 |
+
"model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 986 |
+
"model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
| 987 |
+
"model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 988 |
+
"model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
| 989 |
+
"model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 990 |
+
"model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 991 |
+
"model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 992 |
+
"model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 993 |
+
"model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 994 |
+
"model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 995 |
+
"model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 996 |
+
"model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 997 |
+
"model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 998 |
+
"model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 999 |
+
"model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1000 |
+
"model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1001 |
+
"model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1002 |
+
"model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
| 1003 |
+
"model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 1004 |
+
"model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
| 1005 |
+
"model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 1006 |
+
"model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1007 |
+
"model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1008 |
+
"model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
| 1009 |
+
"model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1010 |
+
"model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 1011 |
+
"model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 1012 |
+
"model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
| 1013 |
+
"model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1014 |
+
"model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
| 1015 |
+
"model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1016 |
+
"model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 1017 |
+
"model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 1018 |
+
"model.shared.weight": "model-00001-of-00003.safetensors"
|
| 1019 |
+
}
|
| 1020 |
+
}
|