Hugging Face's logo

ann-stro
/
roberta_token_new

Token Classification
Transformers
TensorFlow
roberta
Model card Files
xet
Community
ann-stro commited on
Commit
edda677
·
1 Parent(s): b8a5904

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +97 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +51 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +65 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uklfr/gottbert-base",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-DATE",
17
+ "2": "I-DATE",
18
+ "3": "B-DISASTER_TYPE",
19
+ "4": "I-DISASTER_TYPE",
20
+ "5": "B-DISTANCE",
21
+ "6": "I-DISTANCE",
22
+ "7": "B-DURATION",
23
+ "8": "I-DURATION",
24
+ "9": "B-LOCATION",
25
+ "10": "I-LOCATION",
26
+ "11": "B-LOCATION_CITY",
27
+ "12": "I-LOCATION_CITY",
28
+ "13": "B-LOCATION_ROUTE",
29
+ "14": "I-LOCATION_ROUTE",
30
+ "15": "B-LOCATION_STOP",
31
+ "16": "I-LOCATION_STOP",
32
+ "17": "B-LOCATION_STREET",
33
+ "18": "I-LOCATION_STREET",
34
+ "19": "B-NUMBER",
35
+ "20": "I-NUMBER",
36
+ "21": "B-ORGANIZATION",
37
+ "22": "I-ORGANIZATION",
38
+ "23": "B-ORGANIZATION_COMPANY",
39
+ "24": "I-ORGANIZATION_COMPANY",
40
+ "25": "B-ORG_POSITION",
41
+ "26": "I-ORG_POSITION",
42
+ "27": "B-PERSON",
43
+ "28": "I-PERSON",
44
+ "29": "B-TIME",
45
+ "30": "I-TIME",
46
+ "31": "B-TRIGGER",
47
+ "32": "I-TRIGGER"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 3072,
51
+ "label2id": {
52
+ "B-DATE": 1,
53
+ "B-DISASTER_TYPE": 3,
54
+ "B-DISTANCE": 5,
55
+ "B-DURATION": 7,
56
+ "B-LOCATION": 9,
57
+ "B-LOCATION_CITY": 11,
58
+ "B-LOCATION_ROUTE": 13,
59
+ "B-LOCATION_STOP": 15,
60
+ "B-LOCATION_STREET": 17,
61
+ "B-NUMBER": 19,
62
+ "B-ORGANIZATION": 21,
63
+ "B-ORGANIZATION_COMPANY": 23,
64
+ "B-ORG_POSITION": 25,
65
+ "B-PERSON": 27,
66
+ "B-TIME": 29,
67
+ "B-TRIGGER": 31,
68
+ "I-DATE": 2,
69
+ "I-DISASTER_TYPE": 4,
70
+ "I-DISTANCE": 6,
71
+ "I-DURATION": 8,
72
+ "I-LOCATION": 10,
73
+ "I-LOCATION_CITY": 12,
74
+ "I-LOCATION_ROUTE": 14,
75
+ "I-LOCATION_STOP": 16,
76
+ "I-LOCATION_STREET": 18,
77
+ "I-NUMBER": 20,
78
+ "I-ORGANIZATION": 22,
79
+ "I-ORGANIZATION_COMPANY": 24,
80
+ "I-ORG_POSITION": 26,
81
+ "I-PERSON": 28,
82
+ "I-TIME": 30,
83
+ "I-TRIGGER": 32,
84
+ "O": 0
85
+ },
86
+ "layer_norm_eps": 1e-05,
87
+ "max_position_embeddings": 514,
88
+ "model_type": "roberta",
89
+ "num_attention_heads": 12,
90
+ "num_hidden_layers": 12,
91
+ "pad_token_id": 1,
92
+ "position_embedding_type": "absolute",
93
+ "transformers_version": "4.29.2",
94
+ "type_vocab_size": 1,
95
+ "use_cache": true,
96
+ "vocab_size": 52009
97
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa350fcf64a77df2a534d5ae5ffa0b7da014896035792a499e6fc35e916d6184
3
+ size 501966928
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "from_pt": true,
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "<mask>",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff