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 Feb 5 • 35 vwxyzjn/online_dpo_sync Updated Feb 5 • 35 vwxyzjn/ppo_async Updated Feb 5 • 31 vwxyzjn/ppo_sync Updated Feb 5 • 50
lm-human-preference-details vwxyzjn/train_policy_accelerate__sentiment_offline_5k.json__seed1__1696447674 Text Generation • Updated Oct 4, 2023 • 32 lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1 Text Generation • Updated Oct 4, 2023 • 34
vwxyzjn/train_policy_accelerate__sentiment_offline_5k.json__seed1__1696447674 Text Generation • Updated Oct 4, 2023 • 32
lm-human-preference-details/train_policy_accelerate__sentiment_offline_5k.json__seed1 Text Generation • Updated Oct 4, 2023 • 34