Open lxysl opened 4 months ago
Thanks for your nice work. I have a question about whether to predict the \<STOP> token. As seen in the original LLaVA paper, they predict these stop tokens:
and their preprocess codes are: https://github.com/haotian-liu/LLaVA/blob/3e337ad269da3245643a2724a1d694b5839c37f9/llava/train/train.py#L470-L481 but your codes are, which seem not to predict these stop tokens: https://github.com/zhuyiche/llava-phi/blob/5cb6ed1d5f9722b1c37559bed290cca1f866082d/llava_phi/train/train.py#L363-L370 Could you please give some explanations or insights into these differences?
Thanks for your nice work. I have a question about whether to predict the \<STOP> token. As seen in the original LLaVA paper, they predict these stop tokens:
and their preprocess codes are: https://github.com/haotian-liu/LLaVA/blob/3e337ad269da3245643a2724a1d694b5839c37f9/llava/train/train.py#L470-L481 but your codes are, which seem not to predict these stop tokens: https://github.com/zhuyiche/llava-phi/blob/5cb6ed1d5f9722b1c37559bed290cca1f866082d/llava_phi/train/train.py#L363-L370 Could you please give some explanations or insights into these differences?