search

OpenLLMAI / OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
https://openrlhf.readthedocs.io/
Apache License 2.0
1.73k stars 164 forks source link

Fix get_strategy #207

Closed kajyuuen closed 5 months ago

kajyuuen commented 5 months ago

The current implementation does not pass the bf16 option as an argument, and it is always in a state of being True. I will modify it to pass bf16 as an argument.