MesonWarrior commited on
Commit
d802deb
1 Parent(s): 7b20eea

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +42 -0
  2. merges.txt +0 -0
  3. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/rugpt3medium_based_on_gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 2048,
21
+ "n_embd": 1024,
22
+ "n_head": 16,
23
+ "n_inner": null,
24
+ "n_layer": 24,
25
+ "n_positions": 2048,
26
+ "n_special": 0,
27
+ "output_past": true,
28
+ "predict_special_tokens": true,
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.27.4",
40
+ "use_cache": true,
41
+ "vocab_size": 50257
42
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff