Hugging Face's logo

GuiTap
/
bert-large-cased-finetuned-ner-geocorpus

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GuiTap commited on
Commit
56289e3
•
1 Parent(s): ea58296

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +90 -0
  2. model.safetensors +3 -0
  3. runs/Dec04_17-42-48_63b2597b7416/events.out.tfevents.1733334186.63b2597b7416.1245.0 +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
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": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-OTR",
16
+ "2": "I-OTR",
17
+ "3": "B-uniESTG",
18
+ "4": "I-uniESTG",
19
+ "5": "B-sedSLCT",
20
+ "6": "I-sedSLCT",
21
+ "7": "B-EPC",
22
+ "8": "I-EPC",
23
+ "9": "B-bacSED",
24
+ "10": "I-bacSED",
25
+ "11": "B-IDA",
26
+ "12": "I-IDA",
27
+ "13": "B-PRD",
28
+ "14": "I-PRD",
29
+ "15": "B-ctxGBAC",
30
+ "16": "I-ctxGBAC",
31
+ "17": "B-ERA",
32
+ "18": "I-ERA",
33
+ "19": "B-EON",
34
+ "20": "I-EON",
35
+ "21": "B-sedCARB",
36
+ "22": "I-sedCARB",
37
+ "23": "B-sedORGN",
38
+ "24": "I-sedORGN",
39
+ "25": "B-sedQUIM",
40
+ "26": "I-sedQUIM"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 4096,
44
+ "label2id": {
45
+ "B-EON": 19,
46
+ "B-EPC": 7,
47
+ "B-ERA": 17,
48
+ "B-IDA": 11,
49
+ "B-OTR": 1,
50
+ "B-PRD": 13,
51
+ "B-bacSED": 9,
52
+ "B-ctxGBAC": 15,
53
+ "B-sedCARB": 21,
54
+ "B-sedORGN": 23,
55
+ "B-sedQUIM": 25,
56
+ "B-sedSLCT": 5,
57
+ "B-uniESTG": 3,
58
+ "I-EON": 20,
59
+ "I-EPC": 8,
60
+ "I-ERA": 18,
61
+ "I-IDA": 12,
62
+ "I-OTR": 2,
63
+ "I-PRD": 14,
64
+ "I-bacSED": 10,
65
+ "I-ctxGBAC": 16,
66
+ "I-sedCARB": 22,
67
+ "I-sedORGN": 24,
68
+ "I-sedQUIM": 26,
69
+ "I-sedSLCT": 6,
70
+ "I-uniESTG": 4,
71
+ "O": 0
72
+ },
73
+ "layer_norm_eps": 1e-12,
74
+ "max_position_embeddings": 512,
75
+ "model_type": "bert",
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 24,
78
+ "pad_token_id": 0,
79
+ "pooler_fc_size": 768,
80
+ "pooler_num_attention_heads": 12,
81
+ "pooler_num_fc_layers": 3,
82
+ "pooler_size_per_head": 128,
83
+ "pooler_type": "first_token_transform",
84
+ "position_embedding_type": "absolute",
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.46.2",
87
+ "type_vocab_size": 2,
88
+ "use_cache": true,
89
+ "vocab_size": 28996
90
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5965b457e17bb87cf8f8707bf3a71a61da2e64a361641fcfb7c60297e3e0686
3
+ size 1330276172
runs/Dec04_17-42-48_63b2597b7416/events.out.tfevents.1733334186.63b2597b7416.1245.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2352d71f560b15efbb63a25f38418481032fde7632389e59f3c4f8c8e3eefa9
3
+ size 7099
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dbb64094ecd9a9049abafe05401a513854cb6d45c8156413829349ea57ecd3
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff