Hugging Face's logo

Denn231
/
external_clf_v_0.7698

Text Classification
Transformers
Safetensors
bert
text-embeddings-inference
Model card Files
xet
 Community
Denn231 commited on
Commit
076a63b
·
verified ·
1 Parent(s): b915c39

upload from revision 9885391297e0cff57add6ec32dd2cd8d684b90f0

Browse files
Files changed (3) hide show
  1. config.json +37 -33
  2. model.safetensors +2 -2
  3. tokenizer_config.json +21 -58
config.json CHANGED
@@ -1,33 +1,37 @@
1
- {
2
- "_name_or_path": "cointegrated/LaBSE-en-ru",
3
- "architectures": [
4
- "BertForSequenceClassification"
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
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "bert",
18
- "num_attention_heads": 12,
19
- "num_hidden_layers": 12,
20
- "pad_token_id": 0,
21
- "pooler_fc_size": 768,
22
- "pooler_num_attention_heads": 12,
23
- "pooler_num_fc_layers": 3,
24
- "pooler_size_per_head": 128,
25
- "pooler_type": "first_token_transform",
26
- "position_embedding_type": "absolute",
27
- "problem_type": "single_label_classification",
28
- "torch_dtype": "float32",
29
- "transformers_version": "4.47.0",
30
- "type_vocab_size": 2,
31
- "use_cache": true,
32
- "vocab_size": 55083
33
- }
 
 
 
 
 
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
+ "directionality": "bidi",
10
+ "dtype": "float32",
11
+ "eos_token_id": null,
12
+ "gradient_checkpointing": false,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "is_decoder": false,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_position_embeddings": 512,
21
+ "model_type": "bert",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 0,
25
+ "pooler_fc_size": 768,
26
+ "pooler_num_attention_heads": 12,
27
+ "pooler_num_fc_layers": 3,
28
+ "pooler_size_per_head": 128,
29
+ "pooler_type": "first_token_transform",
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "tie_word_embeddings": true,
33
+ "transformers_version": "5.5.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 55083
37
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d69950fa0ab14ecf97270316d20c985d3f3ab267c6fb0963e2549bc54ec88b5
3
- size 513410048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b77ff4f3753673b2bd7b3f04c28ec6ef6183a3dc6591d4aaed3395f6c496384
3
+ size 513410024
tokenizer_config.json CHANGED
@@ -1,58 +1,21 @@
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
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": false,
48
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 512,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
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
+ "max_length": 512,
10
+ "model_max_length": 512,
11
+ "never_split": null,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "stride": 0,
15
+ "strip_accents": null,
16
+ "tokenize_chinese_chars": true,
17
+ "tokenizer_class": "BertTokenizer",
18
+ "truncation_side": "right",
19
+ "truncation_strategy": "longest_first",
20
+ "unk_token": "[UNK]"
21
+ }