goldfish-models
commited on
Commit
•
b114cf1
1
Parent(s):
e743dc7
Upload div_thaa_10mb model.
Browse files- config.json +34 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "models/10mb/div_thaa_10mb",
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50000,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50001,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 512,
|
15 |
+
"n_embd": 512,
|
16 |
+
"n_head": 8,
|
17 |
+
"n_inner": 2048,
|
18 |
+
"n_layer": 4,
|
19 |
+
"n_positions": 512,
|
20 |
+
"pad_token_id": 50002,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.18.0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 51200
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c42aaa3a1672a15326bf329ee3ea02ed226402f878d1dc999104dcd8f8eb536
|
3 |
+
size 157415409
|