EddieChen372 commited on
Commit
966822d
1 Parent(s): f582807

add tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>"
3
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "model_max_length": 2048,
4
+ "name_or_path": "facebook/incoder-1B",
5
+ "special_tokens_map_file": "tokenizer/v2_trfs/special_tokens_map.json",
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }