Name: Shawn/Yuxuan Tong
Type: User
Company: Tsinghua University
Bio: Senior undergraduate @ DCST, Tsinghua University.
Research intern @hkust-nlp (previously: @THUDM).
Interested in LLM & AI for Education/Research/Software Eng.
Twitter: tongyx361
Location: Beijing, China
Blog: tongyx361.github.io
Shawn/Yuxuan Tong's Projects
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Flexible and efficient LLM agent searching algorithm implementation
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
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.
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.
个人整理的《深入理解计算机系统》中文电子版(原书第 3 版)与实验材料:https://hansimov.gitbook.io/csapp/
Shawn Yuxuan Tong's dotfiles
Execute code in text efficiently and safely.
Script that monitors GPU usage on a machine and executes jobs&sends emails when GPUs are available
ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Extra files for Hugging Face Space "ImageReward-in-SD-Web-UI"
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Code for lab of **legal search engine** in *Introduction to Search Engine* (24S) course by Prof. Qingyao Ai @ THU-CST
The official evaluation suite and dynamic data release for MixEval.
nbdev hello world
nbdev template customed by Yuxuan Tong
Test repo for nbdev
A chrome extension to show online dictionary content.
An Olympiad-level bilingual multimodal scientific benchmark, featuring 8,952 questions from Olympiad-level mathematics and physics competitions, including the Chinese college entrance exam.
Examples and guides for using the OpenAI API
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
THU-CST OS-2023A(向勇老师开设)的课后练习 Ex3.1 的解答仓库
Answer to THU-CS OS-2023A-Ex4-1 uCore batch OS procedure analysis
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
Answer Repo to Ex7.1 @ THU-CST OS-2023A (by Prof. Xiang Yong)
Answer Repo to Ex8.1 Python-Simulated File System @ THU-CST OS-2023A (by Prof. Yong Xiang)
QLoRA: Efficient Finetuning of Quantized LLMs