Upload GPTNeoForCausalLM
Browse files- config.json +47 -20
- generation_config.json +2 -2
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,28 +1,55 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/root/pretraining/local-models/training/2024-03-21_17-
|
|
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
|
|
24 |
"torch_dtype": "float32",
|
25 |
"transformers_version": "4.38.0",
|
26 |
"use_cache": true,
|
27 |
-
"vocab_size": 50257
|
|
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/pretraining/local-models/training/2024-03-21_17-29-48",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"classifier_dropout": 0.1,
|
33 |
+
"embed_dropout": 0,
|
34 |
+
"eos_token_id": 50256,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"hidden_size": 768,
|
37 |
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": null,
|
39 |
+
"layer_norm_epsilon": 1e-05,
|
40 |
+
"max_position_embeddings": 2048,
|
41 |
+
"model_type": "gpt_neo",
|
42 |
+
"num_heads": 12,
|
43 |
+
"num_layers": 12,
|
44 |
+
"resid_dropout": 0,
|
45 |
+
"summary_activation": null,
|
46 |
+
"summary_first_dropout": 0.1,
|
47 |
+
"summary_proj_to_labels": true,
|
48 |
+
"summary_type": "cls_index",
|
49 |
+
"summary_use_proj": true,
|
50 |
"torch_dtype": "float32",
|
51 |
"transformers_version": "4.38.0",
|
52 |
"use_cache": true,
|
53 |
+
"vocab_size": 50257,
|
54 |
+
"window_size": 256
|
55 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
"transformers_version": "4.38.0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
"transformers_version": "4.38.0"
|
6 |
}
|
model.safetensors
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 sha256:54121aa1d0755f6c4c2b8735849e71231c5dd170ec37f61ee2b596929b049fd7
|
3 |
+
size 500811336
|