Unify Efficient Fine-Tuning of 100+ LLMs

🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.

The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

Firefly: 大模型训练工具，支持训练Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

A C#/.NET library to run LLM models (🦙LLaMA/LLaVA) on your local device efficiently.

Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3

LlamaIndex is a data framework for your LLM applications

ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs

Python scraper based on AI

Start building LLM-empowered multi-agent applications in an easier way.

🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.

Run LLMs on weak devices or make powerful devices even more powerful by distributing the workload and dividing the RAM usage.

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3