I’m trying to do something fairly basic. When my language model is generating tokens, I want to stop if the language model generates the token corresponding to “##”.
I’m not sure how to do this. Do I need to implement a custom stopping_criteria?
I’m trying to do something fairly basic. When my language model is generating tokens, I want to stop if the language model generates the token corresponding to “##”.
I’m not sure how to do this. Do I need to implement a custom stopping_criteria?