srivatsavaasista commited on
Commit
01ed6f5
1 Parent(s): 27a0bb1

add tokenizer

Browse files
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
  "unk_token": "<|endoftext|>"
6
  }
 
1
  {
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
 
4
  "unk_token": "<|endoftext|>"
5
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
- "name_or_path": "gpt2",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
 
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|>"
vocab.json CHANGED
The diff for this file is too large to render. See raw diff