Yessense commited on
Commit
5377294
·
verified ·
1 Parent(s): 4ec08a7

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +1 -6
  2. model.onnx +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer_config.json +50 -0
config.json CHANGED
@@ -1,14 +1,11 @@
1
  {
2
- "add_cross_attention": false,
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": null,
8
  "classifier_dropout": null,
9
  "dtype": "float32",
10
  "emb_size": 312,
11
- "eos_token_id": null,
12
  "gradient_checkpointing": false,
13
  "hidden_act": "gelu",
14
  "hidden_dropout_prob": 0.1,
@@ -22,7 +19,6 @@
22
  },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 600,
25
- "is_decoder": false,
26
  "label2id": {
27
  "\u0410\u0434\u0435\u043a\u0432\u0430\u0442\u043d\u044b\u0439 \u0437\u0430\u043f\u0440\u043e\u0441": 4,
28
  "\u0412\u043e\u043f\u0440\u043e\u0441 \u043a \u043a\u043b\u0438\u0435\u043d\u0442\u0443": 0,
@@ -38,8 +34,7 @@
38
  "pad_token_id": 0,
39
  "position_embedding_type": "absolute",
40
  "problem_type": "single_label_classification",
41
- "tie_word_embeddings": true,
42
- "transformers_version": "5.0.0",
43
  "type_vocab_size": 2,
44
  "use_cache": false,
45
  "vocab_size": 83828
 
1
  {
 
2
  "architectures": [
3
  "BertForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
 
6
  "classifier_dropout": null,
7
  "dtype": "float32",
8
  "emb_size": 312,
 
9
  "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
 
19
  },
20
  "initializer_range": 0.02,
21
  "intermediate_size": 600,
 
22
  "label2id": {
23
  "\u0410\u0434\u0435\u043a\u0432\u0430\u0442\u043d\u044b\u0439 \u0437\u0430\u043f\u0440\u043e\u0441": 4,
24
  "\u0412\u043e\u043f\u0440\u043e\u0441 \u043a \u043a\u043b\u0438\u0435\u043d\u0442\u0443": 0,
 
34
  "pad_token_id": 0,
35
  "position_embedding_type": "absolute",
36
  "problem_type": "single_label_classification",
37
+ "transformers_version": "4.57.6",
 
38
  "type_vocab_size": 2,
39
  "use_cache": false,
40
  "vocab_size": 83828
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2b8acee81a0072fec0502b5144ae8fa0440a06c64ae09cf58c5dc1ee775297
3
+ size 129195340
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,17 +1,67 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "backend": "tokenizers",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "[CLS]",
5
  "do_basic_tokenize": true,
6
  "do_lower_case": false,
 
7
  "is_local": false,
8
  "mask_token": "[MASK]",
 
9
  "model_max_length": 2048,
10
  "never_split": null,
 
11
  "pad_token": "[PAD]",
 
 
12
  "sep_token": "[SEP]",
 
13
  "strip_accents": null,
14
  "tokenize_chinese_chars": true,
15
  "tokenizer_class": "BertTokenizer",
 
 
16
  "unk_token": "[UNK]"
17
  }
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
  "backend": "tokenizers",
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_basic_tokenize": true,
48
  "do_lower_case": false,
49
+ "extra_special_tokens": {},
50
  "is_local": false,
51
  "mask_token": "[MASK]",
52
+ "max_length": 2048,
53
  "model_max_length": 2048,
54
  "never_split": null,
55
+ "pad_to_multiple_of": null,
56
  "pad_token": "[PAD]",
57
+ "pad_token_type_id": 0,
58
+ "padding_side": "right",
59
  "sep_token": "[SEP]",
60
+ "stride": 0,
61
  "strip_accents": null,
62
  "tokenize_chinese_chars": true,
63
  "tokenizer_class": "BertTokenizer",
64
+ "truncation_side": "right",
65
+ "truncation_strategy": "longest_first",
66
  "unk_token": "[UNK]"
67
  }