Add model files
Browse files- config.json +30 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +8 -0
- tf_model.h5 +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/asimouli/GPT2_MODEL/jean_zay/ckpt-125000",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 1792,
|
17 |
+
"n_head": 14,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 24,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
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": "4.5.1",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 50000
|
30 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd168869a5aabb666963d69ac0be8ccfb49474e75ee11f11c7e29fef6adda2b5
|
3 |
+
size 4092663715
|
special_tokens_map.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"unk_token": "<unk>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"mask_token": "<mask>"
|
7 |
+
}
|
8 |
+
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bad1416cc5deb2aaa6824a6916f3a4342fd333368555283e54cdf888c69c304
|
3 |
+
size 4067702632
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|