Checkpoints for "Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models" https://arxiv.org/abs/2410.18252
Shengyi Costa Huang
vwxyzjn
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
deepseek-ai/DeepSeek-R1-0528
updated
a dataset
2 months ago
vwxyzjn/the-algorithm-python
updated
a dataset
2 months ago
vwxyzjn/rlvr_acecoder
Organizations
The checkpoints are trained in https://arxiv.org/abs/2403.17031 and taken from https://wandb.ai/costa-huang/tldr_summarize/reports/Release--Vmlldzo3MT
-
cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
Text Generation • Updated • 3.47k -
cleanrl/EleutherAI_pythia-1b-deduped__reward__tldr
Text Classification • Updated • 1.89k -
cleanrl/EleutherAI_pythia-2.8b-deduped__sft__tldr
Text Generation • Updated • 2.02k -
cleanrl/EleutherAI_pythia-2.8b-deduped__reward__tldr
Text Classification • Updated • 209
Checkpoints for "Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models" https://arxiv.org/abs/2410.18252
The checkpoints are trained in https://arxiv.org/abs/2403.17031 and taken from https://wandb.ai/costa-huang/tldr_summarize/reports/Release--Vmlldzo3MT
-
cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
Text Generation • Updated • 3.47k -
cleanrl/EleutherAI_pythia-1b-deduped__reward__tldr
Text Classification • Updated • 1.89k -
cleanrl/EleutherAI_pythia-2.8b-deduped__sft__tldr
Text Generation • Updated • 2.02k -
cleanrl/EleutherAI_pythia-2.8b-deduped__reward__tldr
Text Classification • Updated • 209