Karzan commited on
Commit
9024169
1 Parent(s): 6ef3ba4

Upload tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +1 -0
  3. tokenizer_config.json +27 -3
  4. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
 
4
  "unk_token": "<|endoftext|>"
5
  }
 
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
  "unk_token": "<|endoftext|>"
6
  }
tokenizer_config.json CHANGED
@@ -1,9 +1,33 @@
1
  {
 
2
  "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
6
  "model_max_length": 1024,
 
7
  "tokenizer_class": "GPT2Tokenizer",
8
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
9
  }
 
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": 1024,
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