Upload GPTNeoForCausalLM
Browse files- config.json +41 -17
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
CHANGED
@@ -1,30 +1,54 @@
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"initializer_range": 0.02,
|
|
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"n_positions": 1024,
|
18 |
-
"reorder_and_upcast_attn": false,
|
19 |
-
"resid_pdrop": 0.1,
|
20 |
-
"scale_attn_by_inverse_layer_idx": false,
|
21 |
-
"scale_attn_weights": true,
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
24 |
"summary_proj_to_labels": true,
|
25 |
"summary_type": "cls_index",
|
26 |
"summary_use_proj": true,
|
|
|
27 |
"transformers_version": "4.26.0",
|
28 |
"use_cache": true,
|
29 |
-
"vocab_size":
|
30 |
-
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125M",
|
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 |
+
"embed_dropout": 0,
|
33 |
+
"eos_token_id": 50256,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"hidden_size": 768,
|
36 |
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": null,
|
38 |
"layer_norm_epsilon": 1e-05,
|
39 |
+
"max_position_embeddings": 2048,
|
40 |
+
"model_type": "gpt_neo",
|
41 |
+
"num_heads": 12,
|
42 |
+
"num_layers": 12,
|
43 |
+
"resid_dropout": 0,
|
|
|
|
|
|
|
|
|
|
|
44 |
"summary_activation": null,
|
45 |
"summary_first_dropout": 0.1,
|
46 |
"summary_proj_to_labels": true,
|
47 |
"summary_type": "cls_index",
|
48 |
"summary_use_proj": true,
|
49 |
+
"torch_dtype": "float32",
|
50 |
"transformers_version": "4.26.0",
|
51 |
"use_cache": true,
|
52 |
+
"vocab_size": 50259,
|
53 |
+
"window_size": 256
|
54 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.26.0"
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3297f5e66e1ce24443b253351b52bbdcec37a3826a8753608671a8d0cb046edb
|
3 |
+
size 551191249
|