Hugging Face's logo

mrfirdauss
/
roberta_wikiann_conll_finetuned_cv

Token Classification
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
1
mrfirdauss commited on
Commit
f044ff7
•
1 Parent(s): 7c675ee

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +91 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +125 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "philschmid/distilroberta-base-ner-wikiann-conll2003-3-class",
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
+ "finetuning_task": "ner",
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-NAME",
18
+ "2": "I-NAME",
19
+ "3": "B-NATION",
20
+ "4": "I-NATION",
21
+ "5": "B-EMAIL",
22
+ "6": "I-EMAIL",
23
+ "7": "B-URL",
24
+ "8": "I-URL",
25
+ "9": "B-CAMPUS",
26
+ "10": "I-CAMPUS",
27
+ "11": "B-MAJOR",
28
+ "12": "I-MAJOR",
29
+ "13": "B-COMPANY",
30
+ "14": "I-COMPANY",
31
+ "15": "B-DESIGNATION",
32
+ "16": "I-DESIGNATION",
33
+ "17": "B-GPA",
34
+ "18": "I-GPA",
35
+ "19": "B-PHONE NUMBER",
36
+ "20": "I-PHONE NUMBER",
37
+ "21": "B-ACHIEVEMENT",
38
+ "22": "I-ACHIEVEMENT",
39
+ "23": "B-EXPERIENCES DESC",
40
+ "24": "I-EXPERIENCES DESC",
41
+ "25": "B-SKILLS",
42
+ "26": "I-SKILLS",
43
+ "27": "B-PROJECTS",
44
+ "28": "I-PROJECTS"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 3072,
48
+ "label2id": {
49
+ "B-ACHIEVEMENT": 21,
50
+ "B-CAMPUS": 9,
51
+ "B-COMPANY": 13,
52
+ "B-DESIGNATION": 15,
53
+ "B-EMAIL": 5,
54
+ "B-EXPERIENCES DESC": 23,
55
+ "B-GPA": 17,
56
+ "B-MAJOR": 11,
57
+ "B-NAME": 1,
58
+ "B-NATION": 3,
59
+ "B-PHONE NUMBER": 19,
60
+ "B-PROJECTS": 27,
61
+ "B-SKILLS": 25,
62
+ "B-URL": 7,
63
+ "I-ACHIEVEMENT": 22,
64
+ "I-CAMPUS": 10,
65
+ "I-COMPANY": 14,
66
+ "I-DESIGNATION": 16,
67
+ "I-EMAIL": 6,
68
+ "I-EXPERIENCES DESC": 24,
69
+ "I-GPA": 18,
70
+ "I-MAJOR": 12,
71
+ "I-NAME": 2,
72
+ "I-NATION": 4,
73
+ "I-PHONE NUMBER": 20,
74
+ "I-PROJECTS": 28,
75
+ "I-SKILLS": 26,
76
+ "I-URL": 8,
77
+ "O": 0
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "max_position_embeddings": 514,
81
+ "model_type": "roberta",
82
+ "num_attention_heads": 12,
83
+ "num_hidden_layers": 6,
84
+ "pad_token_id": 1,
85
+ "position_embedding_type": "absolute",
86
+ "torch_dtype": "float32",
87
+ "transformers_version": "4.39.3",
88
+ "type_vocab_size": 1,
89
+ "use_cache": true,
90
+ "vocab_size": 50265
91
+ }
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:dc2569f4ae8b91c8f0c3ad7617e57086a9d7cabb1adf6401f251f83f385cbd7a
3
+ size 326212748
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
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": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "id2label": {
51
+ "0": "O",
52
+ "1": "B-NAME",
53
+ "2": "I-NAME",
54
+ "3": "B-NATION",
55
+ "4": "I-NATION",
56
+ "5": "B-EMAIL",
57
+ "6": "I-EMAIL",
58
+ "7": "B-URL",
59
+ "8": "I-URL",
60
+ "9": "B-CAMPUS",
61
+ "10": "I-CAMPUS",
62
+ "11": "B-MAJOR",
63
+ "12": "I-MAJOR",
64
+ "13": "B-COMPANY",
65
+ "14": "I-COMPANY",
66
+ "15": "B-DESIGNATION",
67
+ "16": "I-DESIGNATION",
68
+ "17": "B-GPA",
69
+ "18": "I-GPA",
70
+ "19": "B-PHONE NUMBER",
71
+ "20": "I-PHONE NUMBER",
72
+ "21": "B-ACHIEVEMENT",
73
+ "22": "I-ACHIEVEMENT",
74
+ "23": "B-EXPERIENCES DESC",
75
+ "24": "I-EXPERIENCES DESC",
76
+ "25": "B-SKILLS",
77
+ "26": "I-SKILLS",
78
+ "27": "B-PROJECTS",
79
+ "28": "I-PROJECTS"
80
+ },
81
+ "ignore_mismatched_sizes": true,
82
+ "label2id": {
83
+ "B-ACHIEVEMENT": 21,
84
+ "B-CAMPUS": 9,
85
+ "B-COMPANY": 13,
86
+ "B-DESIGNATION": 15,
87
+ "B-EMAIL": 5,
88
+ "B-EXPERIENCES DESC": 23,
89
+ "B-GPA": 17,
90
+ "B-MAJOR": 11,
91
+ "B-NAME": 1,
92
+ "B-NATION": 3,
93
+ "B-PHONE NUMBER": 19,
94
+ "B-PROJECTS": 27,
95
+ "B-SKILLS": 25,
96
+ "B-URL": 7,
97
+ "I-ACHIEVEMENT": 22,
98
+ "I-CAMPUS": 10,
99
+ "I-COMPANY": 14,
100
+ "I-DESIGNATION": 16,
101
+ "I-EMAIL": 6,
102
+ "I-EXPERIENCES DESC": 24,
103
+ "I-GPA": 18,
104
+ "I-MAJOR": 12,
105
+ "I-NAME": 2,
106
+ "I-NATION": 4,
107
+ "I-PHONE NUMBER": 20,
108
+ "I-PROJECTS": 28,
109
+ "I-SKILLS": 26,
110
+ "I-URL": 8,
111
+ "O": 0
112
+ },
113
+ "mask_token": "<mask>",
114
+ "max_length": 512,
115
+ "model_max_length": 512,
116
+ "num_labels": 29,
117
+ "pad_token": "<pad>",
118
+ "sep_token": "</s>",
119
+ "stride": 0,
120
+ "tokenizer_class": "RobertaTokenizer",
121
+ "trim_offsets": true,
122
+ "truncation_side": "right",
123
+ "truncation_strategy": "longest_first",
124
+ "unk_token": "<unk>"
125
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff