elenanereiss
commited on
Commit
•
a4842ce
1
Parent(s):
2035f6d
Upload 6 files
Browse files- config.json +109 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert512",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "",
|
13 |
+
"1": "B-AN",
|
14 |
+
"2": "B-EUN",
|
15 |
+
"3": "B-GRT",
|
16 |
+
"4": "B-GS",
|
17 |
+
"5": "B-INN",
|
18 |
+
"6": "B-LD",
|
19 |
+
"7": "B-LDS",
|
20 |
+
"8": "B-LIT",
|
21 |
+
"9": "B-MRK",
|
22 |
+
"10": "B-ORG",
|
23 |
+
"11": "B-PER",
|
24 |
+
"12": "B-RR",
|
25 |
+
"13": "B-RS",
|
26 |
+
"14": "B-ST",
|
27 |
+
"15": "B-STR",
|
28 |
+
"16": "B-UN",
|
29 |
+
"17": "B-VO",
|
30 |
+
"18": "B-VS",
|
31 |
+
"19": "B-VT",
|
32 |
+
"20": "I-AN",
|
33 |
+
"21": "I-EUN",
|
34 |
+
"22": "I-GRT",
|
35 |
+
"23": "I-GS",
|
36 |
+
"24": "I-INN",
|
37 |
+
"25": "I-LD",
|
38 |
+
"26": "I-LDS",
|
39 |
+
"27": "I-LIT",
|
40 |
+
"28": "I-MRK",
|
41 |
+
"29": "I-ORG",
|
42 |
+
"30": "I-PER",
|
43 |
+
"31": "I-RR",
|
44 |
+
"32": "I-RS",
|
45 |
+
"33": "I-ST",
|
46 |
+
"34": "I-STR",
|
47 |
+
"35": "I-UN",
|
48 |
+
"36": "I-VO",
|
49 |
+
"37": "I-VS",
|
50 |
+
"38": "I-VT",
|
51 |
+
"39": "O"
|
52 |
+
},
|
53 |
+
"initializer_range": 0.02,
|
54 |
+
"intermediate_size": 3072,
|
55 |
+
"label2id": {
|
56 |
+
"": 0,
|
57 |
+
"B-AN": 1,
|
58 |
+
"B-EUN": 2,
|
59 |
+
"B-GRT": 3,
|
60 |
+
"B-GS": 4,
|
61 |
+
"B-INN": 5,
|
62 |
+
"B-LD": 6,
|
63 |
+
"B-LDS": 7,
|
64 |
+
"B-LIT": 8,
|
65 |
+
"B-MRK": 9,
|
66 |
+
"B-ORG": 10,
|
67 |
+
"B-PER": 11,
|
68 |
+
"B-RR": 12,
|
69 |
+
"B-RS": 13,
|
70 |
+
"B-ST": 14,
|
71 |
+
"B-STR": 15,
|
72 |
+
"B-UN": 16,
|
73 |
+
"B-VO": 17,
|
74 |
+
"B-VS": 18,
|
75 |
+
"B-VT": 19,
|
76 |
+
"I-AN": 20,
|
77 |
+
"I-EUN": 21,
|
78 |
+
"I-GRT": 22,
|
79 |
+
"I-GS": 23,
|
80 |
+
"I-INN": 24,
|
81 |
+
"I-LD": 25,
|
82 |
+
"I-LDS": 26,
|
83 |
+
"I-LIT": 27,
|
84 |
+
"I-MRK": 28,
|
85 |
+
"I-ORG": 29,
|
86 |
+
"I-PER": 30,
|
87 |
+
"I-RR": 31,
|
88 |
+
"I-RS": 32,
|
89 |
+
"I-ST": 33,
|
90 |
+
"I-STR": 34,
|
91 |
+
"I-UN": 35,
|
92 |
+
"I-VO": 36,
|
93 |
+
"I-VS": 37,
|
94 |
+
"I-VT": 38,
|
95 |
+
"O": 39
|
96 |
+
},
|
97 |
+
"layer_norm_eps": 1e-12,
|
98 |
+
"max_position_embeddings": 512,
|
99 |
+
"model_type": "bert",
|
100 |
+
"num_attention_heads": 12,
|
101 |
+
"num_hidden_layers": 12,
|
102 |
+
"pad_token_id": 0,
|
103 |
+
"position_embedding_type": "absolute",
|
104 |
+
"torch_dtype": "float32",
|
105 |
+
"transformers_version": "4.20.1",
|
106 |
+
"type_vocab_size": 2,
|
107 |
+
"use_cache": true,
|
108 |
+
"vocab_size": 30000
|
109 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e856c30dfc54de0c00989a37cc237859191c419aa613d276d394809a82a4aff8
|
3 |
+
size 434156465
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb9f2cf6b0547df93bf8877cf91c8f85b55c57b08cfbc3fab62f615f593f35d7
|
3 |
+
size 434359400
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "bert-base-german-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|