Hugging Face's logo

GuiTap
/
bert-base-multilingual-uncased-finetuned-ner-geocorpus

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GuiTap commited on
Commit
281c295
•
1 Parent(s): e07352e

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +89 -0
  2. model.safetensors +3 -0
  3. runs/Jun02_23-28-12_220f51a1f785/events.out.tfevents.1717370912.220f51a1f785.287.0 +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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
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
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20",
34
+ "21": "LABEL_21",
35
+ "22": "LABEL_22",
36
+ "23": "LABEL_23",
37
+ "24": "LABEL_24",
38
+ "25": "LABEL_25",
39
+ "26": "LABEL_26"
40
+ },
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 3072,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_10": 10,
47
+ "LABEL_11": 11,
48
+ "LABEL_12": 12,
49
+ "LABEL_13": 13,
50
+ "LABEL_14": 14,
51
+ "LABEL_15": 15,
52
+ "LABEL_16": 16,
53
+ "LABEL_17": 17,
54
+ "LABEL_18": 18,
55
+ "LABEL_19": 19,
56
+ "LABEL_2": 2,
57
+ "LABEL_20": 20,
58
+ "LABEL_21": 21,
59
+ "LABEL_22": 22,
60
+ "LABEL_23": 23,
61
+ "LABEL_24": 24,
62
+ "LABEL_25": 25,
63
+ "LABEL_26": 26,
64
+ "LABEL_3": 3,
65
+ "LABEL_4": 4,
66
+ "LABEL_5": 5,
67
+ "LABEL_6": 6,
68
+ "LABEL_7": 7,
69
+ "LABEL_8": 8,
70
+ "LABEL_9": 9
71
+ },
72
+ "layer_norm_eps": 1e-12,
73
+ "max_position_embeddings": 512,
74
+ "model_type": "bert",
75
+ "num_attention_heads": 12,
76
+ "num_hidden_layers": 12,
77
+ "pad_token_id": 0,
78
+ "pooler_fc_size": 768,
79
+ "pooler_num_attention_heads": 12,
80
+ "pooler_num_fc_layers": 3,
81
+ "pooler_size_per_head": 128,
82
+ "pooler_type": "first_token_transform",
83
+ "position_embedding_type": "absolute",
84
+ "torch_dtype": "float32",
85
+ "transformers_version": "4.41.1",
86
+ "type_vocab_size": 2,
87
+ "use_cache": true,
88
+ "vocab_size": 105879
89
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff3c015aa0946ffabc497436b6eebfbfd689a96c8a895b23c09f80a73ae3bf4
3
+ size 667169708
runs/Jun02_23-28-12_220f51a1f785/events.out.tfevents.1717370912.220f51a1f785.287.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78d3935b29298876beb3033fdb9c34764562265f3c0d4077c2f4858039c0256
3
+ size 6915
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e569b4db4ba85b63bf739739fd916f66d8860ed2756f62565216ff2b1232dc4f
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff