scotteinsidler commited on
Commit
603ebf2
1 Parent(s): ad6dffd

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +6 -12
tokenizer_config.json CHANGED
@@ -1,16 +1,10 @@
1
  {
2
  "add_prefix_space": false,
3
- "bos_token": "<s>",
4
- "cls_token": "<s>",
5
- "eos_token": "</s>",
6
- "errors": "replace",
7
- "mask_token": "<mask>",
8
- "model_max_length": 2048,
9
- "name_or_path": "distilroberta-base",
10
- "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
  "special_tokens_map_file": null,
13
- "tokenizer_class": "RobertaTokenizer",
14
- "trim_offsets": true,
15
- "unk_token": "<unk>"
16
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "distilgpt2",
 
 
 
 
 
7
  "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
 
10
  }