Hugging Face's logo

ruchit2801
/
trial-model

Model card Files Community
ruchit2801 commited on
Commit
e0efdc2
•
1 Parent(s): f4f7cb1

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +17 -9
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +32 -13
special_tokens_map.json CHANGED
@@ -1,15 +1,23 @@
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
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
 
 
 
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,34 @@
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
  }
 
1
  {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "use_default_system_prompt": true
34
  }