My learning notes for ML SYS.

贵系 2022 年人智导全部资料，from homework to course review

Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang

Course notes for Cyber Security (THUCST 2023 Spring)

SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper

THUCST Topics in Quantum Computing Summer 2022 Project and Course Note

日本购岛时间中的中日“网络民族主义”分析

A demonstrative example of running SGLang Diffusion with DP router

No repository description provided.

清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University

No repository description provided.

distribution-is-all-you-need is the basic distribution probability tutorial for most common distribution focused on Deep learning using the python library.

No repository description provided.

贵系 2022 春季软工大作业（小组展示得到了全场最高分😯

My work from Summer 2021 till Summer 2022

我的壁纸仓库，主要用来给博客做壁纸

为清华大学答疑坊所写的数据分析脚本

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

A framework for few-shot evaluation of autoregressive language models.

Course homework during 2022 Fall.

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

SAST Skill Docs. We are paving the way for your CS studying.

A jittor implementation of TSIT for jittor AI contest.

数据挖掘

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

赵晨阳写字的地方

Materials for learning SGLang

SGLang is a fast serving framework for large language models and vision language models.

数学实验 2023 春

My official information, designed for PhD application.

Cookbook of SGLang - Recipe

Allow torch tensor memory to be released and resumed later

markdownlint-savior is a Python script designed to assist in resolving common Markdown linting issues. It helps ensure your Markdown files adhere to linting standards and improves the overall quality of your Markdown documents.

No repository description provided.

No repository description provided.

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

No repository description provided.

🎙️Voice input and translation app for macOS. Press to talk, release to paste.

A unified framework for easy reinforcement learning in Flow-Matching models

MrlX: A Multi-Agent Reinforcement Learning Framework

造福广大需要动物实验的朋友

verl: Volcano Engine Reinforcement Learning for LLMs

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

A high-throughput and memory-efficient inference and serving engine for LLMs

No repository description provided.

No repository description provided.

Here is quick script to retrieve HuggingFace Hub Models' {Description}, {Paramerters} and {Download Records} without creeper.

A series of math-specific large language models of our Qwen2 series.

No repository description provided.

No repository description provided.

slime is a LLM post-training framework aiming for RL Scaling.

Distributed RL System for LLM Reasoning

Udpated COPS Code Repo

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Build, evaluate, understand, and fix LLM-based apps

清华大学云盘(Tsinghua Cloud)批量下载脚本，可指定文件类型