The code will be released soon!
You can now load PhotoChat++ from the HuggingFace hub as the following:
from datasets import load_dataset
dataset = load_dataset("passing2961/photochat_plus")
🚨 Disclaimer: Since PhotoChat++ is constructed via crowd-sourcing based on dialogues from the PhotoChat dataset, which is licensed under the CC BY 4.0 International license, PhotoChat++ is shared under the same CC BY 4.0 International license. Therefore, following this license, it is possible to use the PhotoChat++ dataset for commercial purposes. However, we strongly recommend using our dataset for academic and research purposes.
@article{lee2023large,
title={Large Language Models can Share Images, Too!},
author={Lee, Young-Jun and Hyeon, Jonghwan and Choi, Ho-Jin},
journal={arXiv preprint arXiv:2310.14804},
year={2023}
}