Upload OPTForCausalLM
Browse files- config.json +32 -32
- generation_config.json +7 -7
- model.safetensors +1 -1
config.json
CHANGED
@@ -1,32 +1,32 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "facebook/galactica-125m",
|
3 |
-
"_remove_final_layer_norm": false,
|
4 |
-
"activation_dropout": 0.0,
|
5 |
-
"activation_function": "gelu",
|
6 |
-
"architectures": [
|
7 |
-
"OPTForCausalLM"
|
8 |
-
],
|
9 |
-
"attention_dropout": 0.1,
|
10 |
-
"bos_token_id": 0,
|
11 |
-
"do_layer_norm_before": true,
|
12 |
-
"dropout": 0.1,
|
13 |
-
"enable_bias": true,
|
14 |
-
"eos_token_id": 2,
|
15 |
-
"ffn_dim": 3072,
|
16 |
-
"hidden_size": 768,
|
17 |
-
"init_std": 0.02,
|
18 |
-
"layer_norm_elementwise_affine": true,
|
19 |
-
"layerdrop": 0.0,
|
20 |
-
"learned_embeddings": true,
|
21 |
-
"max_position_embeddings": 2048,
|
22 |
-
"model_type": "opt",
|
23 |
-
"num_attention_heads": 12,
|
24 |
-
"num_hidden_layers": 12,
|
25 |
-
"pad_token_id": 1,
|
26 |
-
"scale_embeddings": false,
|
27 |
-
"torch_dtype": "float32",
|
28 |
-
"transformers_version": "4.
|
29 |
-
"use_cache": true,
|
30 |
-
"vocab_size": 50000,
|
31 |
-
"word_embed_proj_dim": 768
|
32 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/galactica-125m",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.1,
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 3072,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"learned_embeddings": true,
|
21 |
+
"max_position_embeddings": 2048,
|
22 |
+
"model_type": "opt",
|
23 |
+
"num_attention_heads": 12,
|
24 |
+
"num_hidden_layers": 12,
|
25 |
+
"pad_token_id": 1,
|
26 |
+
"scale_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.43.0.dev0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 50000,
|
31 |
+
"word_embed_proj_dim": 768
|
32 |
+
}
|
generation_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 0,
|
4 |
-
"eos_token_id": 2,
|
5 |
-
"pad_token_id": 1,
|
6 |
-
"transformers_version": "4.
|
7 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.43.0.dev0"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500144016
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aeb4348c6c079370274b867cdb298c94f66f84ac30a0317ba4b3e7c5b2f3fcb
|
3 |
size 500144016
|