xray1111 commited on
Commit
40b874b
1 Parent(s): f198249

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "tokenizer_class": "LlamaTokenizer",
7
+ "unk_token": "<unk>"
8
+ }