microsoft

/

Phi-3.5-vision-instruct

like 463

https://github.com/2U1/Phi3-Vision-Finetune

I made a fine-tuning script for Phi3.5-Vision. It supprots single-image, multi-image and video dataset.
You can select each module (Vision, LLM, Projector) for fine tuning and set different learning rate for all.

Feedback and issues are welcome!