R0k1e

global-cs-application.github.io

欧港新CS留学项目指北

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

InfiniteBench

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

moderncv

A modern curriculum vitae class for LaTeX

dspy

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

CoGPT

Hmm Copilot or GPT? Who knows. Get access to gpt-4 via copilot.

MatPlotAgent

UltraLink

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

UltraEval

An open source framework for evaluating foundation models.

Guanaco-Model.github.io

BMTrain

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

FedHGNN

The source code of FedHGNN

UltraLink

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

GammaGL

A multi-backend graph learning library.

MiniCPM

MiniCPM-2B: An end-side LLM outperforming Llama2-13B.

UltraEval

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

wikiextractor

A tool for extracting plain text from Wikipedia dumps

OpenCC

Conversion between Traditional and Simplified Chinese

OMGEval

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

LLMZoo

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

ml-mkqa

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 goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Please refer to our paper for details, MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering

vscode

Visual Studio Code

IJCAI-23-PFedRec

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

OpenHGNN

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