la1login commited on
Commit
f6cec8c
1 Parent(s): b34cdb7

manually add model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "B-chem": 55083,
3
+ "I-chem": 55084
4
+ }
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/LaBSE-en-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": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-chem",
16
+ "2": "I-chem"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "B-chem": 1,
22
+ "I-chem": 2,
23
+ "O": 0
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.1",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 55083
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:836dc2e9e9d28a0986f438896c5281be22293054abd12fef3f285355c3428efe
3
+ size 511050564
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "55083": {
44
+ "content": "B-chem",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "55084": {
52
+ "content": "I-chem",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ }
59
+ },
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "do_basic_tokenize": true,
63
+ "do_lower_case": false,
64
+ "mask_token": "[MASK]",
65
+ "model_max_length": 512,
66
+ "never_split": null,
67
+ "pad_token": "[PAD]",
68
+ "sep_token": "[SEP]",
69
+ "strip_accents": null,
70
+ "tokenize_chinese_chars": true,
71
+ "tokenizer_class": "BertTokenizer",
72
+ "unk_token": "[UNK]"
73
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff