Hugging Face's logo

phanerozoic
/
BERT-NER-Classifier

Token Classification
Transformers
Safetensors
English
bert
named-entity-recognition
conll2003
Inference Endpoints
Model card Files Community
phanerozoic commited on
Commit
bd6950f
•
1 Parent(s): 9a50915

Upload 6 files

Browse files
Files changed (5) hide show
  1. config.json +48 -48
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +55 -18
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,48 +1,48 @@
1
- {
2
- "_name_or_path": "bert-base-uncased",
3
- "architectures": [
4
- "BertForTokenClassification"
5
- ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
- "id2label": {
13
- "0": "O",
14
- "1": "B-PER",
15
- "2": "I-PER",
16
- "3": "B-ORG",
17
- "4": "I-ORG",
18
- "5": "B-LOC",
19
- "6": "I-LOC",
20
- "7": "B-MISC",
21
- "8": "I-MISC"
22
- },
23
- "initializer_range": 0.02,
24
- "intermediate_size": 3072,
25
- "label2id": {
26
- "O": 0,
27
- "B-PER": 1,
28
- "I-PER": 2,
29
- "B-ORG": 3,
30
- "I-ORG": 4,
31
- "B-LOC": 5,
32
- "I-LOC": 6,
33
- "B-MISC": 7,
34
- "I-MISC": 8
35
- },
36
- "layer_norm_eps": 1e-12,
37
- "max_position_embeddings": 512,
38
- "model_type": "bert",
39
- "num_attention_heads": 12,
40
- "num_hidden_layers": 12,
41
- "pad_token_id": 0,
42
- "position_embedding_type": "absolute",
43
- "torch_dtype": "float32",
44
- "transformers_version": "4.39.3",
45
- "type_vocab_size": 2,
46
- "use_cache": true,
47
- "vocab_size": 30522
48
- }
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.39.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90813f72cc03711167803332a7efce5b95606adb6168a8e22894140254fa230a
3
+ size 435617620
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,18 +1,55 @@
1
- {
2
- "do_lower_case": true,
3
- "unk_token": "[UNK]",
4
- "sep_token": "[SEP]",
5
- "pad_token": "[PAD]",
6
- "cls_token": "[CLS]",
7
- "mask_token": "[MASK]",
8
- "model_max_length": 512,
9
- "tokenize_chinese_chars": true,
10
- "strip_accents": null,
11
- "do_basic_tokenize": true,
12
- "clean_up_tokenization_spaces": false,
13
- "tokenizer_class": "BertTokenizer",
14
- "special_tokens_map_file": null,
15
- "max_len": 512,
16
- "max_len_single_sentence": 510,
17
- "max_len_sentences_pair": 506
18
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff