The official code of our paper PixelWorld: Towards Perceiving Everything as Pixels.
Refactoring... There may be some problems with the reference relationship between codes.
pip install -r requirements.txtpython data.py --dataset WikiSS_QADataset --model GPT4o --mode text --prompt basepython data.py --dataset WikiSS_QADataset --model GPT4o --mode text --prompt base --from_hf