bs256 version (#1)
Browse files- bs256 version (acebb7407070767e5daaf1f9331fd6bd53615d54)
- config.json +2 -7
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -2,13 +2,8 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"MantaForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"auto_map": {
|
| 6 |
-
"AutoConfig": "configuration_manta.MantaConfig",
|
| 7 |
-
"AutoModel": "modeling_manta.MantaModel",
|
| 8 |
-
"AutoModelForSeq2SeqLM": "modeling_manta.MantaForConditionalGeneration"
|
| 9 |
-
},
|
| 10 |
"byte_embedding_dim": 128,
|
| 11 |
-
"d_ff":
|
| 12 |
"d_kv": 64,
|
| 13 |
"d_model": 768,
|
| 14 |
"dense_act_fn": "gelu_new",
|
|
@@ -22,7 +17,7 @@
|
|
| 22 |
"is_encoder_decoder": true,
|
| 23 |
"is_gated_act": true,
|
| 24 |
"layer_norm_epsilon": 1e-06,
|
| 25 |
-
"max_length_encoder_decoder":
|
| 26 |
"max_length_inputs": 2048,
|
| 27 |
"model_type": "manta",
|
| 28 |
"num_decoder_layers": 12,
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"MantaForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"byte_embedding_dim": 128,
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 768,
|
| 9 |
"dense_act_fn": "gelu_new",
|
|
|
|
| 17 |
"is_encoder_decoder": true,
|
| 18 |
"is_gated_act": true,
|
| 19 |
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"max_length_encoder_decoder": 256,
|
| 21 |
"max_length_inputs": 2048,
|
| 22 |
"model_type": "manta",
|
| 23 |
"num_decoder_layers": 12,
|
pytorch_model.bin
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:c93fe5198c403ace584c8fc1b56770b7497d35deaf8eb82e2ac71d80fcf15219
|
| 3 |
+
size 1024404765
|