liumingzhu6060

liumingzhu6060's starred repositories

Reference implementation for DPO (Direct Preference Optimization)

Language:PythonApache-2.02056 19 81

PaddleSlim is an open-source library for deep model compression and architecture search.

Language:PythonApache-2.01556 92 549

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Language:PythonApache-2.01311 18 84

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

Apache-2.0853 7 22

将视频剪裁贴入到简单的3维盒子模型上，目前未详细整理过代码，纹理的映射坐标还不是很准确。待改进

700