kykim commited on
Commit
859555c
1 Parent(s): ff0f17b

gpt3-small-2700steps

Browse files
Files changed (5) hide show
  1. config.json +28 -0
  2. pytorch_model.bin +3 -0
  3. tf_model.h5 +3 -0
  4. tokenizer_config.json +5 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2Model"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 3,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 3,
10
+ "gradient_checkpointing": false,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 2048,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.1,
21
+ "summary_activation": null,
22
+ "summary_first_dropout": 0.1,
23
+ "summary_proj_to_labels": true,
24
+ "summary_type": "cls_index",
25
+ "summary_use_proj": true,
26
+ "use_cache": true,
27
+ "vocab_size": 42000
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e01921d4eb10a5a78aea2a9a636cb6f9197c6ab97dd95144d3c20ec008f6cb
3
+ size 525899465
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c966ad883d6ac22302742844391f57189762c38f1af35d250ccd5659d9cea9
3
+ size 475713872
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "strip_accents": false,
4
+ "model_max_length": 2048
5
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff