News for hackers. Stuff that matters.
Re:DeepSpeed Chat: Easy, fast and affordable RLHF training o... by valine on Wednesday April 12, 2023 @07:09PM (#35548339)
OpenAssistant has been collecting instruction/response data. They’ve already used that data to refine several llama models with good success.

You can also bootstrap RLHF training data from the gpt4 api. Vicuna is probably the best public model created with gpt4 data available as of today.

There are no comments on this comment yet.