AjayMukundS commited on
Commit
1eea1f6
1 Parent(s): 5ea9c83

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/roberta-large",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
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": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-COURT",
16
+ "2": "I-COURT",
17
+ "3": "B-PETITIONER",
18
+ "4": "I-PETITIONER",
19
+ "5": "B-RESPONDENT",
20
+ "6": "I-RESPONDENT",
21
+ "7": "B-JUDGE",
22
+ "8": "I-JUDGE",
23
+ "9": "B-LAWYER",
24
+ "10": "I-LAWYER",
25
+ "11": "B-DATE",
26
+ "12": "I-DATE",
27
+ "13": "B-ORG",
28
+ "14": "I-ORG",
29
+ "15": "B-GPE",
30
+ "16": "I-GPE",
31
+ "17": "B-STATUTE",
32
+ "18": "I-STATUTE",
33
+ "19": "B-PROVISION",
34
+ "20": "I-PROVISION",
35
+ "21": "B-PRECEDENT",
36
+ "22": "I-PRECEDENT",
37
+ "23": "B-CASE_NUMBER",
38
+ "24": "I-CASE_NUMBER",
39
+ "25": "B-WITNESS",
40
+ "26": "I-WITNESS",
41
+ "27": "B-OTHER_PERSON",
42
+ "28": "I-OTHER_PERSON"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 4096,
46
+ "label2id": {
47
+ "B-CASE_NUMBER": 23,
48
+ "B-COURT": 1,
49
+ "B-DATE": 11,
50
+ "B-GPE": 15,
51
+ "B-JUDGE": 7,
52
+ "B-LAWYER": 9,
53
+ "B-ORG": 13,
54
+ "B-OTHER_PERSON": 27,
55
+ "B-PETITIONER": 3,
56
+ "B-PRECEDENT": 21,
57
+ "B-PROVISION": 19,
58
+ "B-RESPONDENT": 5,
59
+ "B-STATUTE": 17,
60
+ "B-WITNESS": 25,
61
+ "I-CASE_NUMBER": 24,
62
+ "I-COURT": 2,
63
+ "I-DATE": 12,
64
+ "I-GPE": 16,
65
+ "I-JUDGE": 8,
66
+ "I-LAWYER": 10,
67
+ "I-ORG": 14,
68
+ "I-OTHER_PERSON": 28,
69
+ "I-PETITIONER": 4,
70
+ "I-PRECEDENT": 22,
71
+ "I-PROVISION": 20,
72
+ "I-RESPONDENT": 6,
73
+ "I-STATUTE": 18,
74
+ "I-WITNESS": 26,
75
+ "O": 0
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "max_position_embeddings": 514,
79
+ "model_type": "roberta",
80
+ "num_attention_heads": 16,
81
+ "num_hidden_layers": 24,
82
+ "pad_token_id": 1,
83
+ "position_embedding_type": "absolute",
84
+ "torch_dtype": "float32",
85
+ "transformers_version": "4.46.3",
86
+ "type_vocab_size": 1,
87
+ "use_cache": true,
88
+ "vocab_size": 50265
89
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab7292e402079cf993cd0301bbb8e50a27573e89b8f519ade244719c5f0cedb
3
+ size 1417407500
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff