Override build_inputs_with_special_tokens for fast tokenizers (#2912)
* Override build_inputs_with_special_tokens for fast impl + unittest. Signed-off-by: Morgan Funtowicz <morgan@huggingface.co> * Quality + format. Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>
This commit is contained in:
@@ -572,3 +572,11 @@ class BertTokenizerFast(PreTrainedTokenizerFast):
|
||||
)
|
||||
|
||||
self.do_lower_case = do_lower_case
|
||||
|
||||
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
||||
output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
|
||||
|
||||
if token_ids_1:
|
||||
output += token_ids_1 + [self.sep_token_id]
|
||||
|
||||
return output
|
||||
|
||||
Reference in New Issue
Block a user