letz-220 commited on
Commit
9c8494a
1 Parent(s): c062f8e

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +50 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer_config.json +35 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/pgrad/pre_models_pytorch/gpt2-base",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
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": "FC",
13
+ "1": "FD",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "FC": 0,
19
+ "FD": 1,
20
+ "O": 2
21
+ },
22
+ "layer_norm_epsilon": 1e-05,
23
+ "model_type": "gpt2",
24
+ "n_ctx": 1024,
25
+ "n_embd": 768,
26
+ "n_head": 12,
27
+ "n_inner": null,
28
+ "n_layer": 12,
29
+ "n_positions": 1024,
30
+ "problem_type": "single_label_classification",
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.26.1",
48
+ "use_cache": true,
49
+ "vocab_size": 50257
50
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "name_or_path": "/home/pgrad/pre_models_pytorch/gpt2-base",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_fast": true
35
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff