dpo_preference_processor not defined

RLHF-V / RLAIF-V

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

197 stars 6 forks source link

dpo_preference_processor not defined #3

Closed RifleZhang closed 3 months ago

RifleZhang commented 3 months ago

https://github.com/RLHF-V/RLAIF-V/blob/main/muffin/data/data_processors.py#L97

The function is not loaded or defined. Also, gather_data_files_by_glob function may not match the parquet format of open-sourced data. Is it possible to update the dataset/dataloader for result replication? Thanks!

Haoye17 commented 3 months ago

Hi @RifleZhang,

Sorry for the late response and thank you so much for your interest in our work!

We've recently updated the code. In the latest version, the Hugging Face dataset will be automatically downloaded and prepared for use. You can pull the latest code and follow the instructions provided here to start your training.

If you have any other questions, please don't hesitate to ask. We'll be more than happy to assist you!