thomasw21 commited on
Commit
9f96c30
1 Parent(s): 3a667df

Add tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54733cceb3fa9eb9e61b238bd09f4c755b99703841351029e4a4e1b9f21d968a
3
+ size 10629812
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "tokenizer_class": "PreTrainedTokenizerFast"}