SVT-Yang
SVT-Yang
Hello! How do you train your model on RadImageNet、EyePACSp、BCN-20000、HAM-10000 datasets? Are there any masks in these datasets or do they only include medical images? Thanks!
add cache_position=None in MGMllamaForCausalLM.forward() could solve.
> what about multi-image? how should the json cell look like? in terms of image path and image tokens? Hello! Have you figured out? I used multi-image data to finetune...
> > what about multi-image? how should the json cell look like? in terms of image path and image tokens? > > Even for multi-image as per the tutorial you...
> > > Hello! Have you figured out? I used multi-image data to finetune llava-ov-0.5B, but gibberish output. Have you encountered the same situation? Thanks! > > > > >...