llama2-rejection-sampling-before-ppo
OUT premise — entries/2026/06/21/wiki-LLaMA.md
Created 2026-06-21T09:50:09+00:00
Llama 2 introduced rejection sampling before PPO in its RLHF fine-tuning pipeline, departing from the PPO-only approach.
OUT premise — entries/2026/06/21/wiki-LLaMA.md
Created 2026-06-21T09:50:09+00:00
Llama 2 introduced rejection sampling before PPO in its RLHF fine-tuning pipeline, departing from the PPO-only approach.