open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

🐚 OpenDevin: Code Less, Make More

Codebase for Merging Language Models (ICML 2024)

A framework for few-shot evaluation of language models.

Contrastive Language-Image Pretraining

Proxy performance batch tester based on Shadowsocks(R) and V2Ray

An Open-Source Package for Network Embedding (NE)

Geometric Deep Learning Extension Library for PyTorch

Official code for ICLR spotlight paper "InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization"

Source code and dataset for KDD 2020 paper "Adaptive Graph Encoder for Attributed Graph Embedding"

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