training process: mat1 and mat2 must have the same dtype about video-chatgpt HOT 2 CLOSED

Hi @wang9danzuishuai,

Thank you for your interest in our work and accept my apologies for the late reply as I was traveling. The issue is because you set the bf16 to False.

One of the possible solutions is to use FP16 mode by passing --fp16 True to the training command. Please let me know if it works for your GPU. Thank You.

from video-chatgpt.

Hi @wang9danzuishuai,

Thank you for your interest in our work and accept my apologies for the late reply as I was traveling. The issue is because you set the bf16 to False.

One of the possible solutions is to use FP16 mode by passing --fp16 True to the training command. Please let me know if it works for your GPU. Thank You.

Thank you for your reply. I used FP16 mode, but it reminded me that
FlashAttention backward for head dim > 64 requires A100 or H100 GPUs as the implementation needs a large amount of shared memory.
I think it's time for us to buy a new set of GPUs, LOL.

from video-chatgpt.