dpfried commited on
Commit
00e3bf6
1 Parent(s): bbb9990

add tokenizer

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