Hugging Face's logo

sgarbi
/
bert-fda-nutrition-ner

Token Classification
Transformers
Safetensors
English
bert
NER
Inference Endpoints
Model card Files
sgarbi commited on
Commit
649663d
•
1 Parent(s): 487a218

Upload 6 files

Browse files

trained model version 1.0

Files changed (6) hide show
  1. config.json +100 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +55 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "I-VITAMINS",
15
+ "2": "I-STIMULANTS",
16
+ "3": "I-PROXIMATES",
17
+ "4": "I-PROTEIN",
18
+ "5": "I-PROBIOTICS",
19
+ "6": "I-MINERALS",
20
+ "7": "I-LIPIDS",
21
+ "8": "I-FLAVORING",
22
+ "9": "I-ENZYMES",
23
+ "10": "I-EMULSIFIERS",
24
+ "11": "I-DIETARYFIBER",
25
+ "12": "I-COLORANTS",
26
+ "13": "I-CARBOHYDRATES",
27
+ "14": "I-ANTIOXIDANTS",
28
+ "15": "I-ALCOHOLS",
29
+ "16": "I-ADDITIVES",
30
+ "17": "I-ACIDS",
31
+ "18": "B-VITAMINS",
32
+ "19": "B-STIMULANTS",
33
+ "20": "B-PROXIMATES",
34
+ "21": "B-PROTEIN",
35
+ "22": "B-PROBIOTICS",
36
+ "23": "B-MINERALS",
37
+ "24": "B-LIPIDS",
38
+ "25": "B-FLAVORING",
39
+ "26": "B-ENZYMES",
40
+ "27": "B-EMULSIFIERS",
41
+ "28": "B-DIETARYFIBER",
42
+ "29": "B-COLORANTS",
43
+ "30": "B-CARBOHYDRATES",
44
+ "31": "B-ANTIOXIDANTS",
45
+ "32": "B-ALCOHOLS",
46
+ "33": "B-ADDITIVES",
47
+ "34": "B-ACIDS"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 3072,
51
+ "label2id": {
52
+ "O": 0,
53
+ "I-VITAMINS": 1,
54
+ "I-STIMULANTS": 2,
55
+ "I-PROXIMATES": 3,
56
+ "I-PROTEIN": 4,
57
+ "I-PROBIOTICS": 5,
58
+ "I-MINERALS": 6,
59
+ "I-LIPIDS": 7,
60
+ "I-FLAVORING": 8,
61
+ "I-ENZYMES": 9,
62
+ "I-EMULSIFIERS": 10,
63
+ "I-DIETARYFIBER": 11,
64
+ "I-COLORANTS": 12,
65
+ "I-CARBOHYDRATES": 13,
66
+ "I-ANTIOXIDANTS": 14,
67
+ "I-ALCOHOLS": 15,
68
+ "I-ADDITIVES": 16,
69
+ "I-ACIDS": 17,
70
+ "B-VITAMINS": 18,
71
+ "B-STIMULANTS": 19,
72
+ "B-PROXIMATES": 20,
73
+ "B-PROTEIN": 21,
74
+ "B-PROBIOTICS": 22,
75
+ "B-MINERALS": 23,
76
+ "B-LIPIDS": 24,
77
+ "B-FLAVORING": 25,
78
+ "B-ENZYMES": 26,
79
+ "B-EMULSIFIERS": 27,
80
+ "B-DIETARYFIBER": 28,
81
+ "B-COLORANTS": 29,
82
+ "B-CARBOHYDRATES": 30,
83
+ "B-ANTIOXIDANTS": 31,
84
+ "B-ALCOHOLS": 32,
85
+ "B-ADDITIVES": 33,
86
+ "B-ACIDS": 34
87
+ },
88
+ "layer_norm_eps": 1e-12,
89
+ "max_position_embeddings": 512,
90
+ "model_type": "bert",
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 12,
93
+ "pad_token_id": 0,
94
+ "position_embedding_type": "absolute",
95
+ "torch_dtype": "float32",
96
+ "transformers_version": "4.37.2",
97
+ "type_vocab_size": 2,
98
+ "use_cache": true,
99
+ "vocab_size": 30522
100
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92addc152abbaffada426566d90ddf5e7a953d194d49d2a0d9c54edfea493613
3
+ size 435697596
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
The diff for this file is too large to render. See raw diff