sahilnagaralu commited on
Commit
f676091
1 Parent(s): 5f990cf

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +4 -13
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +27 -51
  4. vocab.json +0 -0
special_tokens_map.json CHANGED
@@ -1,15 +1,6 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "pad_token": "</s>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
15
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,33 @@
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": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
 
 
 
 
 
 
49
  "errors": "replace",
50
- "mask_token": "<mask>",
51
- "model_max_length": 1024,
52
- "pad_token": "</s>",
53
- "sep_token": "</s>",
54
- "tokenizer_class": "BartTokenizer",
55
- "trim_offsets": true,
56
- "unk_token": "<unk>"
 
 
 
 
57
  }
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
12
  "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "errors": "replace",
22
+ "model_max_length": 2048,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff