Image-to-Text
Transformers
English
qwen2_vl

Finetuning

#1
by ququwowo - opened

Hi @ziyjiang

Could you guide me on how to fine tune this on a specific data/domain? Which packages to use?

Thank you.

VLM2Vec org

Hi @ququwowo , please checkout our Github package: https://github.com/TIGER-AI-Lab/VLM2Vec
I think to fine-tune on specific data, you only need to write a custom dataloader as in :https://github.com/TIGER-AI-Lab/VLM2Vec/tree/main/src/data/dataset
We are still working on better documents for our codebase. Before that, if you met any issue, please feel free to submit an issue in our repo.

ziyjiang changed discussion status to closed

Sign up or log in to comment