hiroshi-matsuda-rit commited on
Commit
cde3478
·
1 Parent(s): 2df511e

initial commit

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +15 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "<unk|LLM-jp>",
3
+ "bos_token": "<s|LLM-jp>",
4
+ "eos_token": "</s|LLM-jp>",
5
+ "mask_token": "<mask|LLM-jp>",
6
+ "pad_token": "<pad|LLM-jp>",
7
+ "cls_token": "<CLS|LLM-jp>",
8
+ "sep_token": "<SEP|LLM-jp>",
9
+ "eod_token": "<EOD|LLM-jp>",
10
+ "extra_ids": 0,
11
+ "additional_special_tokens": [],
12
+ "sp_model_kwargs": {},
13
+ "do_lower_case": false,
14
+ "tokenizer_class": "PreTrainedTokenizerFast"
15
+ }