JosephusCheung commited on
Commit
96a4996
·
1 Parent(s): 6412ba2

Upload 4 files

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +1 -1
  3. tokenizer_config.json +9 -0
  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
@@ -6,4 +6,4 @@
6
  "bos_token": "<|endoftext|>",
7
  "eos_token": "<|endoftext|>",
8
  "unk_token": "<|endoftext|>"
9
- }
 
6
  "bos_token": "<|endoftext|>",
7
  "eos_token": "<|endoftext|>",
8
  "unk_token": "<|endoftext|>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "tokenizer_class": "GPT2Tokenizer",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff