Hugging Face's logo

nzindoc
/
study-dictionary-roberta-base

Text Classification
Transformers
PyTorch
bert
text-embeddings-inference
Model card Files
xet
Community
1
nzindoc commited on
Commit
5209ace
·
1 Parent(s): e5a5424

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +122 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +15 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "NCT03180736",
15
+ "1": "NCT01985126",
16
+ "2": "NCT03158688",
17
+ "3": "NCT02541383",
18
+ "4": "NCT02076009",
19
+ "5": "NCT01080391",
20
+ "6": "NCT01734928",
21
+ "7": "NCT02963493",
22
+ "8": "NCT01712789",
23
+ "9": "NCT00430365",
24
+ "10": "NCT04557098",
25
+ "11": "NCT03548207",
26
+ "12": "NCT01023308",
27
+ "13": "NCT03412565",
28
+ "14": "NCT02336815",
29
+ "15": "NCT03651128",
30
+ "16": "NCT02252172",
31
+ "17": "NCT02412878",
32
+ "18": "NCT02874742",
33
+ "19": "NCT02990338",
34
+ "20": "NCT03361748",
35
+ "21": "NCT01660633",
36
+ "22": "NCT05066646",
37
+ "23": "NCT02195479",
38
+ "24": "NCT01568866",
39
+ "25": "NCT01239797",
40
+ "26": "NCT02654132",
41
+ "27": "NCT01998971",
42
+ "28": "NCT01311687",
43
+ "29": "NCT00103662",
44
+ "30": "NCT03399799",
45
+ "31": "NCT02136134",
46
+ "32": "NCT03525678",
47
+ "33": "NCT04162210",
48
+ "34": "NCT03110562",
49
+ "35": "NCT01564537",
50
+ "36": "NCT04181827",
51
+ "37": "NCT03151811",
52
+ "38": "NCT05083169",
53
+ "39": "NCT00114101",
54
+ "40": "NCT01554852",
55
+ "41": "ISRCTN17354232",
56
+ "42": "NCT03277105",
57
+ "43": "NCT00551928",
58
+ "44": "NCT03275285"
59
+ },
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "ISRCTN17354232": 41,
64
+ "NCT00103662": 29,
65
+ "NCT00114101": 39,
66
+ "NCT00430365": 9,
67
+ "NCT00551928": 43,
68
+ "NCT01023308": 12,
69
+ "NCT01080391": 5,
70
+ "NCT01239797": 25,
71
+ "NCT01311687": 28,
72
+ "NCT01554852": 40,
73
+ "NCT01564537": 35,
74
+ "NCT01568866": 24,
75
+ "NCT01660633": 21,
76
+ "NCT01712789": 8,
77
+ "NCT01734928": 6,
78
+ "NCT01985126": 1,
79
+ "NCT01998971": 27,
80
+ "NCT02076009": 4,
81
+ "NCT02136134": 31,
82
+ "NCT02195479": 23,
83
+ "NCT02252172": 16,
84
+ "NCT02336815": 14,
85
+ "NCT02412878": 17,
86
+ "NCT02541383": 3,
87
+ "NCT02654132": 26,
88
+ "NCT02874742": 18,
89
+ "NCT02963493": 7,
90
+ "NCT02990338": 19,
91
+ "NCT03110562": 34,
92
+ "NCT03151811": 37,
93
+ "NCT03158688": 2,
94
+ "NCT03180736": 0,
95
+ "NCT03275285": 44,
96
+ "NCT03277105": 42,
97
+ "NCT03361748": 20,
98
+ "NCT03399799": 30,
99
+ "NCT03412565": 13,
100
+ "NCT03525678": 32,
101
+ "NCT03548207": 11,
102
+ "NCT03651128": 15,
103
+ "NCT04162210": 33,
104
+ "NCT04181827": 36,
105
+ "NCT04557098": 10,
106
+ "NCT05066646": 22,
107
+ "NCT05083169": 38
108
+ },
109
+ "layer_norm_eps": 1e-05,
110
+ "max_position_embeddings": 514,
111
+ "model_type": "bert",
112
+ "num_attention_heads": 12,
113
+ "num_hidden_layers": 12,
114
+ "pad_token_id": 1,
115
+ "position_embedding_type": "absolute",
116
+ "problem_type": "multi_label_classification",
117
+ "torch_dtype": "float32",
118
+ "transformers_version": "4.33.2",
119
+ "type_vocab_size": 1,
120
+ "use_cache": true,
121
+ "vocab_size": 50265
122
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d589cab7205ccc01c64b85e87383319a77b849afb098a9b9830a06e53be427
3
+ size 498789297
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a8bffb8f3f76204e194b577c33d4f52132a56bf8974ccbc3496217822268d2
3
+ size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff