Hugging Face's logo

KellyShiiii
/
bert-finetuned-ner

Token Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
KellyShiiii commited on
Commit
a60dcd6
·
1 Parent(s): f2079af

Model save

Browse files
Files changed (6) hide show
  1. config.json +37 -35
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +5 -13
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +10 -16
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,58 +1,60 @@
1
  {
2
- "_name_or_path": "xlm-roberta-base",
3
  "architectures": [
4
- "XLMRobertaForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
  "classifier_dropout": null,
9
- "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "O",
15
- "1": "B-Task",
16
- "2": "I-Task",
17
- "3": "B-Method",
18
- "4": "I-Method",
19
- "5": "B-Metric",
20
- "6": "I-Metric",
21
- "7": "B-Material",
22
- "8": "I-Material",
23
- "9": "B-OtherScientificTerm",
24
- "10": "I-OtherScientificTerm",
25
- "11": "B-Generic",
26
- "12": "I-Generic"
 
 
27
  },
28
  "initializer_range": 0.02,
29
  "intermediate_size": 3072,
30
  "label2id": {
31
- "B-Generic": 11,
32
- "B-Material": 7,
33
- "B-Method": 3,
34
- "B-Metric": 5,
35
- "B-OtherScientificTerm": 9,
36
- "B-Task": 1,
37
- "I-Generic": 12,
38
- "I-Material": 8,
39
- "I-Method": 4,
40
- "I-Metric": 6,
41
- "I-OtherScientificTerm": 10,
42
- "I-Task": 2,
 
 
43
  "O": 0
44
  },
45
- "layer_norm_eps": 1e-05,
46
- "max_position_embeddings": 514,
47
- "model_type": "xlm-roberta",
48
  "num_attention_heads": 12,
49
  "num_hidden_layers": 12,
50
- "output_past": true,
51
- "pad_token_id": 1,
52
  "position_embedding_type": "absolute",
53
  "torch_dtype": "float32",
54
  "transformers_version": "4.23.1",
55
- "type_vocab_size": 1,
56
  "use_cache": true,
57
- "vocab_size": 250002
58
  }
 
1
  {
2
+ "_name_or_path": "./model/sci-bert-30/",
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-MethodName",
15
+ "2": "I-MethodName",
16
+ "3": "B-HyperparameterName",
17
+ "4": "I-HyperparameterName",
18
+ "5": "B-HyperparameterValue",
19
+ "6": "I-HyperparameterValue",
20
+ "7": "B-MetricName",
21
+ "8": "I-MetricName",
22
+ "9": "B-MetricValue",
23
+ "10": "I-MetricValue",
24
+ "11": "B-TaskName",
25
+ "12": "I-TaskName",
26
+ "13": "B-DatasetName",
27
+ "14": "I-DatasetName"
28
  },
29
  "initializer_range": 0.02,
30
  "intermediate_size": 3072,
31
  "label2id": {
32
+ "B-DatasetName": 13,
33
+ "B-HyperparameterName": 3,
34
+ "B-HyperparameterValue": 5,
35
+ "B-MethodName": 1,
36
+ "B-MetricName": 7,
37
+ "B-MetricValue": 9,
38
+ "B-TaskName": 11,
39
+ "I-DatasetName": 14,
40
+ "I-HyperparameterName": 4,
41
+ "I-HyperparameterValue": 6,
42
+ "I-MethodName": 2,
43
+ "I-MetricName": 8,
44
+ "I-MetricValue": 10,
45
+ "I-TaskName": 12,
46
  "O": 0
47
  },
48
+ "layer_norm_eps": 1e-12,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
  "num_attention_heads": 12,
52
  "num_hidden_layers": 12,
53
+ "pad_token_id": 0,
 
54
  "position_embedding_type": "absolute",
55
  "torch_dtype": "float32",
56
  "transformers_version": "4.23.1",
57
+ "type_vocab_size": 2,
58
  "use_cache": true,
59
+ "vocab_size": 28996
60
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:150b3588580fb3b3956202072f28cc1c7d1bb3b7cdffaf2e53b869a4f4e12d90
3
- size 1109928439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb83d982195c4da871bedf9794df930d834e809c66b2b9d471aa653f86c58e3
3
+ size 431000439
special_tokens_map.json CHANGED
@@ -1,15 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
- size 17082758
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb26b43c98e8266ae3e99c2a583cf8315d73b33a17e6b20b4df7ff1f22392d34
3
+ size 669021
tokenizer_config.json CHANGED
@@ -1,20 +1,14 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "__type": "AddedToken",
7
- "content": "<mask>",
8
- "lstrip": true,
9
- "normalized": true,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
  "model_max_length": 512,
14
- "name_or_path": "xlm-roberta-base",
15
- "pad_token": "<pad>",
16
- "sep_token": "</s>",
17
  "special_tokens_map_file": null,
18
- "tokenizer_class": "XLMRobertaTokenizer",
19
- "unk_token": "<unk>"
 
 
20
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
5
  "model_max_length": 512,
6
+ "name_or_path": "./model/sci-bert-30/",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f7591c9c448ec76752639439872eaa2dd88be201af1c5862baf4262b4b0e6e1
3
  size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c3f21e007179e9b708654e38861eff26780180d66d31cb5f8980b876c9afbb
3
  size 3375