Yuhan Chi

TinyLoRA-GRPO-Coder. Inspired by 《Learning to Reason in 13 parameters》, use TinyLoRA+GRPO(32 parameters) to fine-tune Qwen2.5-Coder-3B-Instruct(or other models) to accomplish competitive programming.

github-unflag-playbook-cn. GitHub 账号被 flag / hidden 自救手册：面向中国大陆开发者的申诉流程、SMS验证问题解决方案与真实案例档案 | 中文解封指南 如果这份文档对您有帮助的话，阔不阔以留一个star~(￣▽￣)~*

Qwen4Luogu-RL. This repo can work. But I make some updates in a new repo. Please see more in https://github.com/Chi-Shan0707/TinyLoRA-Qwen-Coder

fdu-opensource-initiative. 复旦开源规范倡议：约定一套统一的 GitHub 仓库命名方式和 Topics 使用规范。

microgpt.cpp. microgpt.cpp in 300 lines!

Query-and-Record-Classical-Chinese-Words. 高中语文文言文学习辅助：查询+记录文言字词中文释义 Chinese Learning

IntuitMath.skill. Teach your AI to teach math the way it was discovered — starting from the crisis, not the definition.

token-verification-mirage. Controlled evaluation of token-level verification signals for LLM math reasoning.

code-not-text. Cross-domain limits of hand-crafted CoT-surface features: AUROC 0.982 in math, 0.434 in coding. Five methods, one conclusion—code correctness is not in the text.

fdu-course-introduction-to-artificial-Intelligence-26spring. 《Introduction to Artificial Intelligence》in Fudan University

fdu-course-programming-25fall. 复旦程序设计

AI4MATH. Shell

ReinforcementLearningHomepage.

Kaggle-Natural-Language-Processing-with-Disaster-Tweets. Natural Language Processing with Disaster Tweets

Baseball. 做一个能看懂【好球】【坏球】的模型。采用数据训练的方式，只要看的比赛录像够多，就能看出好坏球的规则吧。（目前还比较弱，但已经能看懂一些些了惹）

chi-shan0707.github.io. Hi, I am Yuhan Chi.

Kaggle-UrbanFloodBench-Flood-Modelling. UrbanFloodBench: Flood Modelling 一个模块化的，易懂的pytorch版本解答。 如果喜欢，请留下个star PwP / A modularized solution. If you like it, plz star!