Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

RHINE Reality Fallback Enhance LLM

RHINE-VAR Sync Server

Weekly update the Computer Science Paper upload to arxiv.

Alternative backend for y-websocket

Yet another WebUI for Nginx

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Go ahead and axolotl questions

The world's most intuitive and reliable strongly-typed collaborative library

[Windows / Mac / Linux / Android / iOS] Maybe the best all-rounded service app for Fudan University students. 可能是复旦学生最好的第三方校园服务APP。

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

通过自然语言询问，能够自动生成SQL语句在数据库中检索信息，展示数据，并判断是否适合绘制图表并绘制，并做出最后总结。

Resources for my Udemy course

GUI for a Vocal Remover that uses Deep Neural Networks.

Bilibili Downloader. 一个命令行式哔哩哔哩下载器.

Official code for the paper: InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (previously: Do Role-Playing Chatbots Capture the Character Persona…

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

图形块代码生成，类似谷歌的Blockly。

《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients.

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

👻 Primitive and flexible state management for React

🧙 Valtio makes proxy-state simple for React and Vanilla

Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)