Stars
5
stars
written in Python
Clear filter
Making large AI models cheaper, faster and more accessible
Train transformer language models with reinforcement learning.
Azur Lane bot (CN/EN/JP/TW) 碧蓝航线脚本 | 无缝委托科研，全自动大世界
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
PyTorch implementation of Super SloMo by Jiang et al.