tongyx361
Senior undergraduate @ DCST, Tsinghua University. Research intern @hkust-nlp (previously: @THUDM). Interested in LLM & AI for Education/Research/Software Eng.
Tsinghua UniversityBeijing, China
Pinned Repositories
dart-math
[NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Awesome-LLM-Research
Curation of resources for LLM research, screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.
Awesome-LLM4Math
Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.
nbdev-template-tongyx361
nbdev template customed by Yuxuan Tong
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
reward-by-prm800k
sample-difficulty-adaptive-tuning
Code from project *Sample-Difficulty-Adaptive Supervised Fine-Tuning for Mathematical Reasoning* at course ANN-23F@THU-CST
symeval
Evaluation utilities based on SymPy.
tongyx361's Repositories
tongyx361/Awesome-LLM4Math
Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.
tongyx361/Awesome-LLM-Research
Curation of resources for LLM research, screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.
tongyx361/symeval
Evaluation utilities based on SymPy.
tongyx361/reward-by-prm800k
tongyx361/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
tongyx361/sample-difficulty-adaptive-tuning
Code from project *Sample-Difficulty-Adaptive Supervised Fine-Tuning for Mathematical Reasoning* at course ANN-23F@THU-CST
tongyx361/dotfiles
Shawn Yuxuan Tong's dotfiles
tongyx361/execode
Execute code in text efficiently and safely.
tongyx361/legal-search
Code for lab of **legal search engine** in *Introduction to Search Engine* (24S) course by Prof. Qingyao Ai @ THU-CST
tongyx361/nbdev-template-tongyx361
nbdev template customed by Yuxuan Tong
tongyx361/OS-2023A-Ex7-1-eBPF
Answer Repo to Ex7.1 @ THU-CST OS-2023A (by Prof. Xiang Yong)
tongyx361/agent-search
Flexible and efficient LLM agent searching algorithm implementation
tongyx361/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
tongyx361/cod-lab2
tongyx361/MixEval
The official evaluation suite and dynamic data release for MixEval.
tongyx361/nbdev-hello-world
nbdev hello world
tongyx361/nbdev-test
Test repo for nbdev
tongyx361/nextjs-dashboard
tongyx361/OlympiadBench
An Olympiad-level bilingual multimodal scientific benchmark, featuring 8,952 questions from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam.
tongyx361/OS-2023A-Ex4-1-uCore-batch-OS-procedure-analysis
Answer to THU-CS OS-2023A-Ex4-1 uCore batch OS procedure analysis
tongyx361/OS-2023A-Ex6-1-Secondary-Page-Table
THU-CST OS-2023A（向勇老师开设）的课后练习 Ex6.1 “二级页表”的解答仓库
tongyx361/OS-Ex8-1-Python-Simulated-File-System
Answer Repo to Ex8.1 Python-Simulated File System @ THU-CST OS-2023A (by Prof. Yong Xiang)
tongyx361/psp-lab1-viz-fourier-series
Lab 1 *Visualization of Fourier Series* in course *Principles of Signal Processing* by Prof. Jia Jia at DSCT, THU
tongyx361/Qwen2.5-Math
A series of math-specific large language models of our Qwen2 series.
tongyx361/SpinalTemplateMill
A simple SpinalHDL demo project based on Mill
tongyx361/tongyx361.github.io
(Shawn) Yuxuan Tong's Homepage
tongyx361/VinePPO
Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"
tongyx361/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
tongyx361/ZeroEval
A simple unified framework for evaluating LLMs
tongyx361/zhihu-md-pub
Markdown (and related files) to publish on Zhihu.