llama3

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted 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. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference

api kubernetes ai text-generation distributed tts image-generation llama mamba libp2p gemma mistral audio-generation llm stable-diffusion rwkv gpt4all musicgen rerank llama3

UpdatedJul 18, 2025
Go

khoj-ai /khoj

Sponsor

Star30.6k

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

chat agent productivity research ai emacs self-hosted assistant image-generation obsidian stt semantic-search rag obsidian-md llm chatgpt whatsapp-ai llamacpp offline-llm llama3

UpdatedJul 18, 2025
Python

datawhalechina /self-llm

Star21.6k

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

lora llm chatglm qwen chatglm3 internlm2 minicpm qwen2 qwen1-5 glm-4 gemma-2b-it llama3 q-wen

UpdatedJul 5, 2025
Jupyter Notebook

1Panel-dev /MaxKB

Star17.2k

🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。

agent chatbot knowledgebase rag llm langchain pgvector ollama maxkb llama3 agentic-ai mcp-server deepseek-r1 qwen3

UpdatedJul 18, 2025
Python

sgl-project /sglang

Star16.1k

SGLang is a fast serving framework for large language models and vision language models.

cuda inference pytorch transformer openai moe llama vlm kimi blackwell llm llm-serving llava deepseek llama3 deepseek-v3 deepseek-r1 qwen3 llama4 llama5

UpdatedJul 18, 2025
Python

xorbitsai /inference

Star8.3k

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.

machine-learning deployment inference pytorch artificial-intelligence llama whisper gemma mistral openai-api llm flan-t5 chatglm llamacpp vllm ggml wizardlm qwen llama3 glm4

UpdatedJul 18, 2025
Python

modelscope /agentscope

Star7.6k

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

agent drag-and-drop mcp chatbot multi-agent multi-modal distributed-agents gpt-4 large-language-models llm llm-agent llama3 gpt-4o

UpdatedJul 17, 2025
Python

InternLM /lmdeploy

Star6.7k

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

llama cuda-kernels deepspeed llm fastertransformer llm-inference turbomind internlm llama2 codellama llama3

UpdatedJul 18, 2025
Python

yangjianxin1 /Firefly

Star6.5k

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、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

llama gpt lora gemma alpaca zephyr mistral peft aquila baichuan llm chatglm qlora internlm llama2 qwen mixtral minicpm qwen2 llama3

UpdatedOct 24, 2024
Python

open-compass /opencompass

Star5.7k

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.

benchmark evaluation openai llm chatgpt large-language-model llama2 llama3