Open dinhanhx opened 4 months ago
Thanks for your advice! The core of M3 is here https://github.com/mu-cai/matryoshka-mm/blob/main/llava/model/llava_arch.py#L147
Let me know if you have further questions!
What is the value range of matryoshka_vis_token_scale
? From 1 to infinity? Or 0.0 to 1.0?
Hi, the range is shown here: https://github.com/mu-cai/matryoshka-mm/blob/main/scripts/v1_5/finetune.sh#L36
Discussion
I know the paper is being reviewed and will likely be modified. However, I think some sort of pseudocode would be nice. Few chunks of paragraphs make things a bit hard to follow. The pseudocode also would help other people implement this technique onto their current models.