trlx
There are 2 repositories under trlx topic.
vicgalle/zero-shot-reward-models
ZYN: Zero-Shot Reward Models with Yes-No Questions
ssbuild/llm_rlhf
realize the reinforcement learning training for gpt2 llama bloom and so on llm model
There are 2 repositories under trlx topic.
ZYN: Zero-Shot Reward Models with Yes-No Questions
realize the reinforcement learning training for gpt2 llama bloom and so on llm model