lmms-lab vs llava-hf

[amew0]

I want to understand on the use of Model Architecture difference between the author release of lmms-lab and the HF team releases on llava-hf. For the same set of Models does using one over the another has performance difference?

And is there any plans to transfer weights trained on one to another. I want this since I want to do vLLM inferences but they only support the ones developed by llava-hf

[NicoZenith]

Hi, I posted an issue 1 month ago about this topic: #193
By following the script and adapting it to your own checkpoints, you can convert your lmms-lab into llava-hf format and perform inference with the huggingface library.

[amew0]

Thank you I will check it out