-
OpenRLHF Public
Forked from OpenRLHF/OpenRLHFAn Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
-
-
-
cycada Public
Forked from jhoffman/cycada_releaseCode to accompany ICML 2018 paper
Python BSD 2-Clause "Simplified" License UpdatedAug 25, 2022 -
-
-
luckmatters Public
Forked from facebookresearch/luckmattersUnderstanding Training Dynamics of Deep ReLU Networks
Python Other UpdatedSep 17, 2021