nishimura999 commited on
Commit
bc3607d
1 Parent(s): f0c6425

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +10 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +18 -0
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<CLS|LLM-jp>",
4
+ "eod_token": "</s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<MASK|LLM-jp>",
7
+ "pad_token": "<PAD|LLM-jp>",
8
+ "sep_token": "<SEP|LLM-jp>",
9
+ "unk_token": "<unk>"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "unk_token": "<unk>",
5
+ "bos_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "pad_token": "<PAD|LLM-jp>",
8
+ "cls_token": "<CLS|LLM-jp>",
9
+ "sep_token": "<SEP|LLM-jp>",
10
+ "eod_token": "</s>",
11
+ "mask_token": "<MASK|LLM-jp>",
12
+ "extra_ids": 0,
13
+ "sp_model_kwargs": {},
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "clean_up_tokenization_spaces": false,
16
+ "special_tokens_map_file": null,
17
+ "tokenizer_class": "PreTrainedTokenizerFast"
18
+ }