Yisheng Bao
Yisheng Bao
@Bilibilee Hi, I'm encountering the same issue regarding the token inconsistency between training stages. Could you share how you resolved this, specifically: 1. How did you handle the token mismatch...
@zjutkarma Hi, I'm having both issues you mentioned: 1. The `mm_projector` KeyError when loading QFormer weights 2. The token number mismatch between LLaMA lm_head (33) and config.num_new_tokens (35) Could you...
@zjutkarma Thanks! It helps me a lot.