LMFlow
LMFlow copied to clipboard
Where are the beginning and end tokens of text added?
Where are the beginning and end tokens of text added?
I am looking for the start token and end token in the code where are they added. But i can not find it. Maybe I left it out. Can you tell me where it is?
Thank you!
Thanks for your interest in LMFlow! Currently we didn't add the start and end token. For start token, as there will always be inputs from user, we deem it optional. As for end token, it is an issue that we will be fixed in the near future. Currently you may manually add customized end marks at the end of samples (e.g. "###") during finetuning, and use --end_string ###
for examples/chatbot.py
during inference to end the output properly. Thanks 😄
This issue has been marked as stale because it has not had recent activity. If you think this still needs to be addressed please feel free to reopen this issue. Thanks