a.korepanov commited on
Commit
50282f3
1 Parent(s): 887cf1c

safetensors update

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -1
  2. config.json +2 -2
  3. pytorch_model.bin +0 -3
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +44 -2
.gitattributes CHANGED
@@ -29,4 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
- pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zstandard filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -55,8 +55,8 @@
55
  "pooler_type": "first_token_transform",
56
  "position_embedding_type": "absolute",
57
  "torch_dtype": "float16",
58
- "transformers_version": "4.20.1",
59
  "type_vocab_size": 2,
60
  "use_cache": true,
61
  "vocab_size": 120138
62
- }
 
55
  "pooler_type": "first_token_transform",
56
  "position_embedding_type": "absolute",
57
  "torch_dtype": "float16",
58
+ "transformers_version": "4.36.2",
59
  "type_vocab_size": 2,
60
  "use_cache": true,
61
  "vocab_size": 120138
62
+ }
pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0928d162fd53b902c8aa1704cb29f904d777398c152e0c6a5cdc676d6cf397c
3
- size 851804225
 
 
 
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,55 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "cls_token": "[CLS]",
3
  "do_basic_tokenize": true,
4
  "do_lower_case": true,
5
  "mask_token": "[MASK]",
6
- "name_or_path": "sberbank-ai/sbert_large_nlu_ru",
7
  "never_split": null,
8
  "pad_token": "[PAD]",
9
  "sep_token": "[SEP]",
10
- "special_tokens_map_file": null,
11
  "strip_accents": false,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "BertTokenizer",
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
  "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": false,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",