Haoran Wang

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

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

[ICLR'25] Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

Deep Reinforcement Learning spring 24, Tsinghua Univ.

清华大学计算机系科协暑期培训-爬虫入门

No description.

计算机系薛巍教授《并行计算基础》24秋

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

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

🙌 OpenHands: AI-Driven Development

Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.

Scripts to change your wallpaper directly on Macos. Pictures are downloaded from Bing

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

No description.

No description.

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

No description.

Tsinghua Univ. ANN 2024 HW. Lecturer: Minlie Huang

Reimplementation of robomimic [https://github.com/ARISE-Initiative/robomimic]

Intelligent Systems and Robotics; Lecturer: Jianyu Chen

Basic skills training 24 - Linux & Shell, Tsinghua Univ.

Tsinghua Univ. DM 2024 Proj, Personal Loan Violation Prediction.

No description.

本 demo 的起因是：我被一个奇怪的 CAPTCHA 背刺了

No description.

Implementation for ACE-Off-Policy-Actor-Critic-with-Causality-Aware-Entropy-Regularization

No description.

A parallel programming training mini app simulating weather-like flows

Java HW for Summer23, in Tsinghua Univ.

HW for Fundamental of Programming, Autumn 23, in THU.

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