nlpxucan / WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

decoding not stop in WizardMath

Ricardokevins opened this issue · comments

In wizard math 7b, i use the model.generate to inference, but model will generate a lot of
And to my surprise, it's not the special token.

How to prevent this when using model.generate? ( generating a lot of waste a lot of time)