Sahajtomar commited on
Commit
0a0e969
1 Parent(s): b625194

First version of the NER_legal_de

Browse files
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\Lenovo\\PycharmProjects\\pythonProject\\Legal NER",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "id2label": {
12
+ "0": "B-AN",
13
+ "1": "B-EUN",
14
+ "2": "B-GRT",
15
+ "3": "B-GS",
16
+ "4": "B-INN",
17
+ "5": "B-LD",
18
+ "6": "B-LDS",
19
+ "7": "B-LIT",
20
+ "8": "B-MRK",
21
+ "9": "B-ORG",
22
+ "10": "B-PER",
23
+ "11": "B-RR",
24
+ "12": "B-RS",
25
+ "13": "B-ST",
26
+ "14": "B-STR",
27
+ "15": "B-UN",
28
+ "16": "B-VO",
29
+ "17": "B-VS",
30
+ "18": "B-VT",
31
+ "19": "I-AN",
32
+ "20": "I-EUN",
33
+ "21": "I-GRT",
34
+ "22": "I-GS",
35
+ "23": "I-INN",
36
+ "24": "I-LD",
37
+ "25": "I-LDS",
38
+ "26": "I-LIT",
39
+ "27": "I-MRK",
40
+ "28": "I-ORG",
41
+ "29": "I-PER",
42
+ "30": "I-RR",
43
+ "31": "I-RS",
44
+ "32": "I-ST",
45
+ "33": "I-STR",
46
+ "34": "I-UN",
47
+ "35": "I-VO",
48
+ "36": "I-VS",
49
+ "37": "I-VT",
50
+ "38": "O"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 4096,
54
+ "label2id": {
55
+ "B-AN": 0,
56
+ "B-EUN": 1,
57
+ "B-GRT": 2,
58
+ "B-GS": 3,
59
+ "B-INN": 4,
60
+ "B-LD": 5,
61
+ "B-LDS": 6,
62
+ "B-LIT": 7,
63
+ "B-MRK": 8,
64
+ "B-ORG": 9,
65
+ "B-PER": 10,
66
+ "B-RR": 11,
67
+ "B-RS": 12,
68
+ "B-ST": 13,
69
+ "B-STR": 14,
70
+ "B-UN": 15,
71
+ "B-VO": 16,
72
+ "B-VS": 17,
73
+ "B-VT": 18,
74
+ "I-AN": 19,
75
+ "I-EUN": 20,
76
+ "I-GRT": 21,
77
+ "I-GS": 22,
78
+ "I-INN": 23,
79
+ "I-LD": 24,
80
+ "I-LDS": 25,
81
+ "I-LIT": 26,
82
+ "I-MRK": 27,
83
+ "I-ORG": 28,
84
+ "I-PER": 29,
85
+ "I-RR": 30,
86
+ "I-RS": 31,
87
+ "I-ST": 32,
88
+ "I-STR": 33,
89
+ "I-UN": 34,
90
+ "I-VO": 35,
91
+ "I-VS": 36,
92
+ "I-VT": 37,
93
+ "O": 38
94
+ },
95
+ "layer_norm_eps": 1e-12,
96
+ "max_position_embeddings": 512,
97
+ "model_type": "bert",
98
+ "num_attention_heads": 16,
99
+ "num_hidden_layers": 24,
100
+ "pad_token_id": 0,
101
+ "type_vocab_size": 2,
102
+ "vocab_size": 31102
103
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc6c77cf2446106744b820538e15caf10f548d68560572622dd7e8fd4453ace
3
+ size 1339074999
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0d552e6558801034fb902ea85427b97bbb9b4eddd16a6c931d503adf2cde7b
3
+ size 1343618924
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "max_len": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "deepset/gbert-large"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292dc8e88e9cda03461dae5cc0446345c6f0f0ee98e335c701f2595f991287fe
3
+ size 1775
vocab.txt ADDED
The diff for this file is too large to render. See raw diff