Pinned Loading

1. AIXueRLHF AIXueRLHF Public

   Forked from zhurou603/AIXueRLHF

   AIXueRLHF强化学习框架：基于TRL库的PPO源码，结合个性化教学业务，修改得到AIXueRLHF。

   Python

2. AIXueTeacher AIXueTeacher Public

   基于 TRL 的 DPO 算法和 PPO 变体 AIXueRLHF，后训练 AIXueTeacher 解决教学决策中的 bad case 问题。

   Python

3. aixue-rlhf-vf aixue-rlhf-vf Public

   AIXueRLHF的value function，用于预测基于当前policy model的学生表现。AIXueRLHF仓库链接：https://github.com/Leslie-Jiang-99/AIXueRLHF

   Jupyter Notebook 1

4. RisKVA RisKVA Public

   RisKVA - Risk Assessment VLM Assistant

   Jupyter Notebook

5. math-tutor-chatai math-tutor-chatai Public

   Jupyter Notebook

6. transformer-source-code-interpretation transformer-source-code-interpretation Public

   Forked from harvardnlp/annotated-transformer

   本仓库旨在解读 transformer 的源码。参考的源码来自 https://github.com/harvardnlp/annotated-transformer

   Jupyter Notebook