Hugging Face's logo

sofia-uni
/
toxic-bert-bg

Text Classification
Safetensors
Bulgarian
bert
Model card Files Community
melaniab commited on
Commit
0163dcf
•
1 Parent(s): 031049e

Add model files

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -0
  2. config.json +79 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. spiece.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +58 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<pad>": 119547,
3
+ "<unk>": 119548
4
+ }
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rmihaylov/bert-base-bg",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "by_layer_is_trainable": {
8
+ "0": true,
9
+ "1": true,
10
+ "10": true,
11
+ "11": true,
12
+ "12": true,
13
+ "13": true,
14
+ "14": true,
15
+ "15": true,
16
+ "16": true,
17
+ "17": true,
18
+ "18": true,
19
+ "19": true,
20
+ "2": true,
21
+ "20": true,
22
+ "21": true,
23
+ "22": true,
24
+ "23": true,
25
+ "3": true,
26
+ "4": true,
27
+ "5": true,
28
+ "6": true,
29
+ "7": true,
30
+ "8": true,
31
+ "9": true
32
+ },
33
+ "classifier_dropout": null,
34
+ "cls_trainable": true,
35
+ "directionality": "bidi",
36
+ "embedding_postprocessor_trainable": true,
37
+ "embeddings_layer_norm_trainable": true,
38
+ "hidden_act": "gelu",
39
+ "hidden_dropout_prob": 0.1,
40
+ "hidden_size": 768,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1",
44
+ "2": "LABEL_2",
45
+ "3": "LABEL_3"
46
+ },
47
+ "init_optimizer_variables": true,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 3072,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1,
53
+ "LABEL_2": 2,
54
+ "LABEL_3": 3
55
+ },
56
+ "layer_norm_eps": 1e-12,
57
+ "max_position_embeddings": 512,
58
+ "model_type": "bert",
59
+ "num_attention_heads": 12,
60
+ "num_hidden_layers": 12,
61
+ "pad_token_id": 0,
62
+ "pooler_fc_size": 768,
63
+ "pooler_num_attention_heads": 12,
64
+ "pooler_num_fc_layers": 3,
65
+ "pooler_size_per_head": 128,
66
+ "pooler_trainable": true,
67
+ "pooler_type": "first_token_transform",
68
+ "position_embedding_type": "absolute",
69
+ "position_embeddings_trainable": true,
70
+ "problem_type": "single_label_classification",
71
+ "token_type_trainable": true,
72
+ "torch_dtype": "float32",
73
+ "transformer_trainable": true,
74
+ "transformers_version": "4.41.2",
75
+ "type_vocab_size": 2,
76
+ "use_cache": true,
77
+ "vocab_size": 119547,
78
+ "word_embeddings_trainable": true
79
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84290d980b4c2a2937ba870029f2c9eb0cf26dd68b679d6f137b8b1fffad52a
3
+ size 711449608
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335602b8eb9d6c18b5ebc116bdb92f3e1d1673a47253c97fc37dfae43dd01042
3
+ size 3337490
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
+ "2": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "3": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "4": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "119547": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "119548": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "keep_accents": true,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "remove_space": true,
54
+ "sep_token": "[SEP]",
55
+ "sp_model_kwargs": {},
56
+ "tokenizer_class": "AlbertTokenizer",
57
+ "unk_token": "<unk>"
58
+ }