Hugging Face's logo

slickdata
/
finetuned-Sentiment-classfication-ROBERTA-model

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
slickdata commited on
Commit
42e6295
•
1 Parent(s): 24e64dc

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +7 -43
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +8 -56
  4. vocab.json +0 -0
special_tokens_map.json CHANGED
@@ -1,51 +1,15 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,63 +1,15 @@
1
  {
2
  "add_prefix_space": false,
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
- "mask_token": {
30
- "__type": "AddedToken",
31
- "content": "<mask>",
32
- "lstrip": true,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
  "model_max_length": 512,
38
- "pad_token": {
39
- "__type": "AddedToken",
40
- "content": "<pad>",
41
- "lstrip": false,
42
- "normalized": true,
43
- "rstrip": false,
44
- "single_word": false
45
- },
46
- "sep_token": {
47
- "__type": "AddedToken",
48
- "content": "</s>",
49
- "lstrip": false,
50
- "normalized": true,
51
- "rstrip": false,
52
- "single_word": false
53
- },
54
  "tokenizer_class": "RobertaTokenizer",
55
- "unk_token": {
56
- "__type": "AddedToken",
57
- "content": "<unk>",
58
- "lstrip": false,
59
- "normalized": true,
60
- "rstrip": false,
61
- "single_word": false
62
- }
63
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "bos_token": "<s>",
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "errors": "replace",
8
+ "mask_token": "<mask>",
 
 
 
 
 
 
 
9
  "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
15
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff