How to prepare 2023-02-12_oasst_prod.jsonl

[ghtaro]

Hi,

I am trying to run sample scripts in https://github.com/LAION-AI/Open-Assistant/tree/main/model. I would to run RL training script, but I could not prepare oasst dataset specified in config yml.

It would be very helpful if you tell me how to do it.

[andreaskoepf]

The OA dataset has not been released. If you want to prepare training code you can look at a sample of 100 English trees here: https://github.com/Open-Assistant/oasst-model-eval/blob/main/model_eval/manual/data/en_100_tree.jsonl

If you are interested in helping us to train the RL model please join the OA discord and ping me (or other members of the dev team).

[huangtao36]

Are there any open datasets where I can try to train it

[ghtaro]

@andreaskoepf Thank you very much for your reply. I managed to run RL training with WebGPT, but will definitely try en_100_tree and visit OA discord!