Do interesting things
基本信息/Basic Info
- 中国-上海 / China - Shanghai
- GitHub: Chi-Shan0707
我目前在读于复旦大学数学科学学院。同时一直在坚持自学计算机当中一些有意思的内容。
最近做了不少有意思的东西
希望能找到自己真正想交叉,研究的东西。
I am currently an undergraduate student at the School of Mathematical Sciences, Fudan University.
At the same time, I have been persistently self-studying interesting topics in Computer Science.
I’ve been working on several exciting projects recently, hoping to find the perfect intersection where my research interests lie.
我的仓库/My repos
数个kaggle repo link比赛,广泛了解并使用了各种机器学习工具。
Participated in several Kaggle competitions, gaining broad exposure to and practical experience with various machine learning tools.一个CNN+ResNet18,学好球坏球判断的模型repo link
A Strike/Ball Classification Model using CNN + ResNet18 for baseball pitch analysis.微调qwen三部曲: 从传统sft,到“复现”《learning to reason in 13 parameters》 论文的tinylora(或是全github首发),到优化数据集和奖励函数,增加test和validrepo link
The “Qwen Fine-tuning Trilogy”: From traditional [SFT], to “reproducing” the Learning to Reason in 13 Parameters paper using TinyLoRA (possibly the first implementation on GitHub), and finally to optimizing datasets and reward functions with added testing and validation.对于高级算法和mc++的一些探索会在Hone My C Plus Plus中
Explorations of Advanced Algorithms and Modern C++ can be found in [Hone My C Plus Plus].- 带随机数的算法的精髓在于看似随机,但是每次随机选择都能选的不是很差,是sample的艺术。同时在这我初步浅尝了java,故名曰Sample Java。
The essence of Randomized Algorithms lies in the “Art of Sampling”—making choices that appear random but are statistically effective. This repo also marks my first taste of Java, hence the name [Sample Java]. The majority of the repo is my stduy notes. - 这三个仓库 DeepLearning、GenerativeModel 与 ReinforcementLearning 是我的学习记录,涵盖了从理论推导到代码复现的过程。
These three repositories serve as my learning records, covering the journey from theoretical derivation to code implementation in Deep Learning, Generative Models, and Reinforcement Learning.
技术工具栈/Tech stack and tools
| Domain | Skills |
|---|---|
| Language | |
| IDE | |
| OS | |
| Other |
