Atsuyuki Miyai

icon indicating a website link https://atsumiyai.github.io/

icon company The University of Tokyo icon location Japan, Tokyo icon location I'm Atsuyuki Miyai, a 1st-year PhD student at The University of Tokyo.

Results 4 comments of Atsuyuki Miyai

LLaVA-1.5 Inference Without Images Not Working Properly

I also encountered the same problem. Does anyone know the solution for the inference of LLaVA-1.5 without images?

LLaVA-1.5 Inference Without Images Not Working Properly

@haotian-liu @chancharikmitra Thanks for your reply. By referring to `model_vqa_science.py`, I found that I added DEFAULT_IMAGE_TOKEN to qs, which causes errors. By removing DEFAULT_IMAGE_TOKEN, this error can be solved. Thanks...

LLaVA-1.5 Inference Without Images Not Working Properly

Thanks! @chancharikmitra @copperwiring Thanks for your question! Could you check whether `image_token_se` is added in L61-70 in `run_llava.py`? `image_token_se` is unnecessary for this case, so you can skip these processes...

Update the Postmill Image

Me too! I cannot access the above link. Can you provide this? https://drive.google.com/drive/folders/1lboUgbt_rUrS9DtHH8XX0onECJju8BBh?usp=sharing