🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

A modular graph-based Retrieval-Augmented Generation (RAG) system

CVPR2023 talking face implementation for Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.

Production-ready platform for agentic workflow development.

A generalized information-seeking agent system with Large Language Models (LLMs).

Collection of Open Source Projects Related to GPT，GPT相关开源项目合集🚀、精选🔥🔥

LangChain结合了大型语言模型、知识库和计算逻辑，可以用于快速开发强大的AI应用。这个仓库包含了我对LangChain的学习和实践经验，包括教程和代码案例。让我们一起探索LangChain的可能性，共同推动人工智能领域的进步！

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。

fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。

🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途

中文langchain项目|小必应，Q.Talk，强聊，QiangTalk

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

中文Guanaco(原驼)大语言模型 QLora 量化训练 +本地CPU/GPU部署 (Chinese Guanaco QLoRA: Efficient Finetuning of Quantized LLMs)

ChatGPT资料汇总学习，持续更新......

Multi-language Enhanced LLaMA

A collection of libraries to optimise AI model performances

收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中

PlantsVsZombies game made by cocos2dx 3.16 (c++)

PyTorch implementation of AnimeGANv2

we want to create a repo to illustrate usage of transformers in chinese

PyTorch 官方中文教程包含 60 分钟快速入门教程，强化教程，计算机视觉，自然语言处理，生成对抗网络，强化学习。欢迎 Star，Fork！

知乎文章干货汇总，包含机器学习、数据分析、Python、可视化、vscode等内容，欢迎收藏学习，点赞支持

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Clone a voice in 5 seconds to generate arbitrary speech in real-time

pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。