search

Instruction-Tuning-with-GPT-4 / GPT-4-LLM

Instruction Tuning with GPT-4
https://instruction-tuning-with-gpt-4.github.io/
Apache License 2.0
4.22k stars 302 forks source link

Is the OPT 1.3B reward model open-source? #20

Closed Symbolk closed 1 year ago

Symbolk commented 1 year ago

I learn from the paper that "To evaluate data quality, we train a reward model based on OPT 1.3B (Iyer et al., 2022) to rate different responses.", can it be used as a replacement for GPT-4 at the rewarding task? Is it open-sourced?

Instruction-Tuning-with-GPT-4 commented 1 year ago

Thanks for your interests. For now, we can not release any additional resources but we defenitely will release the model. Stay tuned.