How to Fine Tune Google PaliGemma, a Vision Language Model?

[@proterotype]

I appreciate your walk through of the Quantize & LoRA parts!

[@1murali5teja]

Thank you mervin, your knowledge is awesome, please share this type of videos. We need this videos. I have been practicing from your videos only

[@squiddymute]

wouldn't be important to know how can you make your custom data to train it with?

[@francycharuto]

They often neglect that

[@kolasatheesh1719]

hey mervin how to create the medical instruction tuning dataset...

[@manasikhillare5646]

Thankyou Mervin ! I really appreciate the walk through I was hoping to clear a doubt. While running the code on my dataset, there is no training_args.bin created in the repo. and the inputs are unable to infer channel dimension format. would it be because of this file?

[@nurusterling8024]

Just fine tuned this for object detection. Getting very poor performance. What could be the issue?

[@prudhvi6e380]

Are you using the quantized version?