Hugging Face's logo

rrivera1849
/
LUAR-CRUD

Feature Extraction
Transformers
PyTorch
Safetensors
English
LUAR
custom_code
Model card Files Community
1
rrivera1849 commited on
Commit
56d1818
·
verified ·
1 Parent(s): 13c4b5b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +49 -58
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - en
 
5
  ---
6
 
7
  # rrivera1849/LUAR-CRUD
 
1
  ---
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  ---
6
 
7
  # rrivera1849/LUAR-CRUD
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,66 +1,57 @@
1
  {
2
  "add_prefix_space": false,
3
- "add_special_tokens": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": true,
13
- "cls_token": {
14
- "__type": "AddedToken",
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "eos_token": {
22
- "__type": "AddedToken",
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": true,
26
- "rstrip": false,
27
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
 
 
 
 
29
  "errors": "replace",
30
- "full_tokenizer_file": null,
31
- "mask_token": {
32
- "__type": "AddedToken",
33
- "content": "<mask>",
34
- "lstrip": true,
35
- "normalized": true,
36
- "rstrip": false,
37
- "single_word": false
38
- },
39
  "model_max_length": 512,
40
- "pad_token": {
41
- "__type": "AddedToken",
42
- "content": "<pad>",
43
- "lstrip": false,
44
- "normalized": true,
45
- "rstrip": false,
46
- "single_word": false
47
- },
48
- "sep_token": {
49
- "__type": "AddedToken",
50
- "content": "</s>",
51
- "lstrip": false,
52
- "normalized": true,
53
- "rstrip": false,
54
- "single_word": false
55
- },
56
  "tokenizer_class": "RobertaTokenizer",
57
  "trim_offsets": true,
58
- "unk_token": {
59
- "__type": "AddedToken",
60
- "content": "<unk>",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false
65
- }
66
  }
 
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
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
  "errors": "replace",
50
+ "mask_token": "<mask>",
 
 
 
 
 
 
 
 
51
  "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  "tokenizer_class": "RobertaTokenizer",
55
  "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
57
  }