Xenova HF Staff commited on
Commit
6ca4715
·
verified ·
1 Parent(s): 615841e

Upload 2 files

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +28 -8
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,14 +1,34 @@
1
  {
 
2
  "add_prefix_space": false,
3
- "additional_special_tokens": null,
4
- "backend": "tokenizers",
5
- "bos_token": "<|endoftext|>",
6
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "errors": "replace",
8
- "is_local": false,
9
  "model_max_length": 512,
10
- "pad_token": "[PAD]",
11
  "padding_side": "right",
12
  "tokenizer_class": "GPT2Tokenizer",
13
- "unk_token": "<|endoftext|>"
14
- }
 
 
 
 
 
 
 
 
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": 512,
23
+ "pad_token": null,
24
  "padding_side": "right",
25
  "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }