wannaphong
commited on
Commit
•
be87413
1
Parent(s):
ec6565c
add model
Browse files- config.json +53 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./thaigpt-next-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 |
+
"transformers_version": "4.6.1",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 50258,
|
52 |
+
"window_size": 256
|
53 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3dd6d968ab94d138528b48006e9b42d4d367234d2f7d7a1888768d770f8f855
|
3 |
+
size 526020725
|