Tanrei commited on
Commit
72c1049
1 Parent(s): aa9ca65

Upload tokenizer

Browse files
Files changed (4) hide show
  1. emoji.json +0 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +11 -0
  4. vocab.txt +0 -0
emoji.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "do_clean_text": false,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "name_or_path": "abeja/gpt-neox-japanese-2.7b",
7
+ "pad_token": "<|endoftext|>",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "GPTNeoXJapaneseTokenizer",
10
+ "unk_token": "<|endoftext|>"
11
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff