Hugging Face's logo

Alexanrd
/
sbert_punc_case_ru_onnx

ONNX
bert
Model card Files Community
Alexanrd commited on
Commit
6577e7a
·
verified ·
1 Parent(s): 175dd00

Загрузка модели

Browse files
Files changed (6) hide show
  1. config.json +62 -0
  2. model.onnx +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +58 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kontur-ai/sbert_punc_case_ru",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "-100": "O",
15
+ "1": "LOWER_O",
16
+ "2": "LOWER_PERIOD",
17
+ "3": "LOWER_COMMA",
18
+ "4": "LOWER_QUESTION",
19
+ "5": "UPPER_O",
20
+ "6": "UPPER_PERIOD",
21
+ "7": "UPPER_COMMA",
22
+ "8": "UPPER_QUESTION",
23
+ "9": "UPPER_TOTAL_O",
24
+ "10": "UPPER_TOTAL_PERIOD",
25
+ "11": "UPPER_TOTAL_COMMA",
26
+ "12": "UPPER_TOTAL_QUESTION"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 4096,
30
+ "label2id": {
31
+ "LOWER_COMMA": 3,
32
+ "LOWER_O": 1,
33
+ "LOWER_PERIOD": 2,
34
+ "LOWER_QUESTION": 4,
35
+ "O": -100,
36
+ "UPPER_COMMA": 7,
37
+ "UPPER_O": 5,
38
+ "UPPER_PERIOD": 6,
39
+ "UPPER_QUESTION": 8,
40
+ "UPPER_TOTAL_COMMA": 11,
41
+ "UPPER_TOTAL_O": 9,
42
+ "UPPER_TOTAL_PERIOD": 10,
43
+ "UPPER_TOTAL_QUESTION": 12
44
+ },
45
+ "layer_norm_eps": 1e-12,
46
+ "max_position_embeddings": 512,
47
+ "model_type": "bert",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 24,
50
+ "pad_token_id": 0,
51
+ "pooler_fc_size": 768,
52
+ "pooler_num_attention_heads": 12,
53
+ "pooler_num_fc_layers": 3,
54
+ "pooler_size_per_head": 128,
55
+ "pooler_type": "first_token_transform",
56
+ "position_embedding_type": "absolute",
57
+ "torch_dtype": "float16",
58
+ "transformers_version": "4.48.3",
59
+ "type_vocab_size": 2,
60
+ "use_cache": true,
61
+ "vocab_size": 120138
62
+ }
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:370ec84ca27874b3c6d261a45a4804bb6d625b6689c3500eadd9ef5101152f5f
3
+ size 1704085570
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": false,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff