alert pad_token source

Former-commit-id: f26a84e0d927d2554890daf431a93652e18f4235
This commit is contained in:
hiyouga
2023-08-15 00:07:56 +08:00
parent 7f0b908de2
commit ef2ca0a827
2 changed files with 5 additions and 2 deletions

View File

@@ -204,7 +204,10 @@ def get_template_and_fix_tokenizer(
logger.info("Add eos token: {}".format(tokenizer.eos_token))
if tokenizer.pad_token_id is None:
tokenizer.pad_token = tokenizer.eos_token
if tokenizer.unk_token_id is not None:
tokenizer.pad_token = tokenizer.unk_token
else:
tokenizer.pad_token = tokenizer.eos_token
logger.info("Add pad token: {}".format(tokenizer.pad_token))
tokenizer.add_special_tokens(dict(additional_special_tokens=template.stop_words))