Hugging Face's logo

rasmodev
/
Covid-19_Sentiment_Analysis_RoBERTa_Model

Text Classification
Transformers
PyTorch
Safetensors
roberta
Inference Endpoints
Model card Files Community
19
rasmodev commited on
Commit
fb3987b
•
1 Parent(s): eb034e6

Upload tokenizer (#6)

Browse files

- Upload tokenizer (19430c988900676cfbbbfa6220dc4be24a27c242)

Files changed (4) hide show
  1. added_tokens.json +7 -0
  2. special_tokens_map.json +1 -7
  3. tokenizer.json +4 -4
  4. tokenizer_config.json +49 -55
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
special_tokens_map.json CHANGED
@@ -2,13 +2,7 @@
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>"
 
2
  "bos_token": "<s>",
3
  "cls_token": "<s>",
4
  "eos_token": "</s>",
5
+ "mask_token": "<mask>",
 
 
 
 
 
 
6
  "pad_token": "<pad>",
7
  "sep_token": "</s>",
8
  "unk_token": "<unk>"
tokenizer.json CHANGED
@@ -23,7 +23,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": false,
27
  "special": true
28
  },
29
  {
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": false,
36
  "special": true
37
  },
38
  {
@@ -41,7 +41,7 @@
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
- "normalized": false,
45
  "special": true
46
  },
47
  {
@@ -50,7 +50,7 @@
50
  "single_word": false,
51
  "lstrip": false,
52
  "rstrip": false,
53
- "normalized": false,
54
  "special": true
55
  },
56
  {
 
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
+ "normalized": true,
27
  "special": true
28
  },
29
  {
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
+ "normalized": true,
36
  "special": true
37
  },
38
  {
 
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
44
+ "normalized": true,
45
  "special": true
46
  },
47
  {
 
50
  "single_word": false,
51
  "lstrip": false,
52
  "rstrip": false,
53
+ "normalized": true,
54
  "special": true
55
  },
56
  {
tokenizer_config.json CHANGED
@@ -1,65 +1,59 @@
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": 1000000000000000019884624838656,
38
  "num_labels": 3,
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
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
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
+ "additional_special_tokens": [],
46
+ "bos_token": "<s>",
47
  "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  "errors": "replace",
51
+ "mask_token": "<mask>",
 
 
 
 
 
 
 
52
  "model_max_length": 1000000000000000019884624838656,
53
  "num_labels": 3,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  "tokenizer_class": "RobertaTokenizer",
57
  "trim_offsets": true,
58
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
59
  }