Python API and command-line tool for Sci-Hub

Up-to-date simple useragent faker with real world database

Coroutine-based concurrency library for Python

欧港新CS留学项目指北

OpenChat: Advancing Open-source Language Models with Imperfect Data

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

A modern curriculum vitae class for LaTeX

DSPy: The framework for programming—not prompting—foundation models

An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset

An open source framework for evaluating foundation models.

Efficient Training (including pre-training and fine-tuning) for Big Models

The source code of FedHGNN

An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset

A multi-backend graph learning library.

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

[ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.

A tool for extracting plain text from Wikipedia dumps

Conversion between Traditional and Simplified Chinese

OMGEval😮: An Open Multilingual Generative Evaluation Benchmark for Foundation Models

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The…

Visual Studio Code

Code for ijcai-23 paper "Dual Personalization on Federated Recommendation"

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.