Hugging Face's logo

truongnguyenxuanvinh
/
goemotions_1

Text Classification
Transformers
Safetensors
xlm-roberta
Inference Endpoints
Model card Files Community
truongnguyenxuanvinh commited on
Commit
c87bc9b
·
verified ·
1 Parent(s): bf30185

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +6 -42
  2. tokenizer_config.json +7 -8
special_tokens_map.json CHANGED
@@ -1,25 +1,7 @@
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,
@@ -27,25 +9,7 @@
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,
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
tokenizer_config.json CHANGED
@@ -1,10 +1,9 @@
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
@@ -12,7 +11,7 @@
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,7 +19,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,12 +27,12 @@
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,
@@ -47,11 +46,11 @@
47
  "cls_token": "<s>",
48
  "do_lower_case": true,
49
  "eos_token": "</s>",
50
- "errors": "replace",
51
  "mask_token": "<mask>",
52
  "model_max_length": 512,
53
  "pad_token": "<pad>",
54
  "sep_token": "</s>",
55
- "tokenizer_class": "RobertaTokenizer",
 
56
  "unk_token": "<unk>"
57
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<s>",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
11
  "1": {
12
  "content": "<pad>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
27
  "3": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "250001": {
36
  "content": "<mask>",
37
  "lstrip": true,
38
  "normalized": false,
 
46
  "cls_token": "<s>",
47
  "do_lower_case": true,
48
  "eos_token": "</s>",
 
49
  "mask_token": "<mask>",
50
  "model_max_length": 512,
51
  "pad_token": "<pad>",
52
  "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
  "unk_token": "<unk>"
56
  }