Async RLHF Paper Checkpoints Checkpoints for "Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models" https://arxiv.org/abs/2410.18252 vwxyzjn/online_dpo_async Updated 18 days ago • 39 vwxyzjn/online_dpo_sync Updated 18 days ago • 26 vwxyzjn/ppo_async Updated 18 days ago • 22 vwxyzjn/ppo_sync Updated 18 days ago • 36
lm-human-preference-details vwxyzjn/train_policy_accelerate__sentiment_offline_5k.json__seed1__1696447674 Text Generation • Updated Oct 4, 2023 • 72 lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1 Text Generation • Updated Oct 4, 2023 • 80
vwxyzjn/train_policy_accelerate__sentiment_offline_5k.json__seed1__1696447674 Text Generation • Updated Oct 4, 2023 • 72
lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1 Text Generation • Updated Oct 4, 2023 • 80