harshildarji
commited on
Commit
•
790177f
1
Parent(s):
7da621f
pt and tf models upload
Browse files- config.json +110 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./gbert-legal-ner",
|
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": "B-LIT",
|
14 |
+
"1": "B-VT",
|
15 |
+
"2": "I-VO",
|
16 |
+
"3": "I-GS",
|
17 |
+
"4": "B-RR",
|
18 |
+
"5": "I-VS",
|
19 |
+
"6": "I-LIT",
|
20 |
+
"7": "B-EUN",
|
21 |
+
"8": "I-UN",
|
22 |
+
"9": "B-VS",
|
23 |
+
"10": "B-AN",
|
24 |
+
"11": "I-PER",
|
25 |
+
"12": "B-VO",
|
26 |
+
"13": "I-INN",
|
27 |
+
"14": "B-MRK",
|
28 |
+
"15": "B-LDS",
|
29 |
+
"16": "I-RR",
|
30 |
+
"17": "I-VT",
|
31 |
+
"18": "I-ORG",
|
32 |
+
"19": "I-RS",
|
33 |
+
"20": "B-INN",
|
34 |
+
"21": "I-ST",
|
35 |
+
"22": "I-LDS",
|
36 |
+
"23": "B-GRT",
|
37 |
+
"24": "O",
|
38 |
+
"25": "B-ORG",
|
39 |
+
"26": "I-LD",
|
40 |
+
"27": "I-STR",
|
41 |
+
"28": "B-LD",
|
42 |
+
"29": "B-PER",
|
43 |
+
"30": "I-GRT",
|
44 |
+
"31": "I-EUN",
|
45 |
+
"32": "B-ST",
|
46 |
+
"33": "B-STR",
|
47 |
+
"34": "B-UN",
|
48 |
+
"35": "B-RS",
|
49 |
+
"36": "I-AN",
|
50 |
+
"37": "B-GS",
|
51 |
+
"38": "I-MRK",
|
52 |
+
"39": "PAD"
|
53 |
+
},
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"B-AN": 10,
|
58 |
+
"B-EUN": 7,
|
59 |
+
"B-GRT": 23,
|
60 |
+
"B-GS": 37,
|
61 |
+
"B-INN": 20,
|
62 |
+
"B-LD": 28,
|
63 |
+
"B-LDS": 15,
|
64 |
+
"B-LIT": 0,
|
65 |
+
"B-MRK": 14,
|
66 |
+
"B-ORG": 25,
|
67 |
+
"B-PER": 29,
|
68 |
+
"B-RR": 4,
|
69 |
+
"B-RS": 35,
|
70 |
+
"B-ST": 32,
|
71 |
+
"B-STR": 33,
|
72 |
+
"B-UN": 34,
|
73 |
+
"B-VO": 12,
|
74 |
+
"B-VS": 9,
|
75 |
+
"B-VT": 1,
|
76 |
+
"I-AN": 36,
|
77 |
+
"I-EUN": 31,
|
78 |
+
"I-GRT": 30,
|
79 |
+
"I-GS": 3,
|
80 |
+
"I-INN": 13,
|
81 |
+
"I-LD": 26,
|
82 |
+
"I-LDS": 22,
|
83 |
+
"I-LIT": 6,
|
84 |
+
"I-MRK": 38,
|
85 |
+
"I-ORG": 18,
|
86 |
+
"I-PER": 11,
|
87 |
+
"I-RR": 16,
|
88 |
+
"I-RS": 19,
|
89 |
+
"I-ST": 21,
|
90 |
+
"I-STR": 27,
|
91 |
+
"I-UN": 8,
|
92 |
+
"I-VO": 2,
|
93 |
+
"I-VS": 5,
|
94 |
+
"I-VT": 17,
|
95 |
+
"O": 24,
|
96 |
+
"PAD": 39
|
97 |
+
},
|
98 |
+
"layer_norm_eps": 1e-12,
|
99 |
+
"max_position_embeddings": 512,
|
100 |
+
"model_type": "bert",
|
101 |
+
"num_attention_heads": 12,
|
102 |
+
"num_hidden_layers": 12,
|
103 |
+
"pad_token_id": 0,
|
104 |
+
"position_embedding_type": "absolute",
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.10.2",
|
107 |
+
"type_vocab_size": 2,
|
108 |
+
"use_cache": true,
|
109 |
+
"vocab_size": 30000
|
110 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1b2781c8f494cc6f2efdc62c0a2a655a82e63f3ccdaa4b0cc962f70101577c9
|
3 |
+
size 434169457
|
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 sha256:5735e69c8fb16772b82f758e6c41aa7bff5ccf59023372302689caeda8e826ce
|
3 |
+
size 434354272
|
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": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-german-cased", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|