HappynessI

Prefix_GRPO. This repository contains experimental reports and training results for my research

review-material. C++（From TJU）

Prompts_For_All_Work. Store my exploration in AI prompts and share my insights

TJU-CV. TeX

Digital_museum. This is the frontend of the "Trace the Origin, Nourish the Mind with Culture" Practice Team.

SimpleRL-Reason-replication. This repository contains experimental reports and training results for a replication of the SimpleRL_Reason project, specifically documenting outcomes from training on the qwen2.5-math-1.5b model.

Simple_RLHF. The reproduction of a simple RL project, supporting Google Colab

League_of_Idea. Python