Showing 1-20 of 40 projects
Run open-source AI models locally with Ollama, supporting multiple frameworks and integrations.
Fine-tuning framework for 100+ LLMs & VLMs
All-in-one AI app for local and remote LLM usage with RAG, agents, and MCP compatibility
Fine-tuning & RL for LLMs with optimized performance and memory use
VybeGuide.ai discovery platform for vibe coders
Deprecated Llama 3 repository with links to updated Llama Stack components
Comprehensive guide for Chinese developers to deploy and fine-tune open-source LLMs on Linux
Open-source platform for building enterprise-grade agents with RAG, workflows, and MCP tools
LLM agents built for real-world use, designed for control and deployed in minutes.
An implementation of the LLaMA model, built one matrix multiplication at a time using Jupyter Notebooks.
Deploy open-source LLMs as OpenAI-compatible API endpoints using BentoML's model serving framework.
Unified, production-ready inference API to run open-source, speech, and multimodal models on cloud, on-prem, or your laptop.
A comprehensive SDK for running frontier LLMs and VLMs on multiple hardware platforms with day-0 model support.
LMDeploy is a toolkit for compressing, deploying, and serving large language models (LLMs).
OpenCompass is a comprehensive LLM evaluation platform supporting a wide range of models and datasets.
Firefly is a comprehensive toolkit for training large language models like Qwen, Llama, Baichuan, and more, targeting AI-focused developers.
AI-powered note-taking and knowledge management for developers, with intelligent connections and ChatGPT integration.
Repairs invalid JSON from LLMs using a Python module
Jupyter Notebook project to build large language models from scratch using Python, including GLM4, Llama3, and RWKV6.
A comprehensive collection of resources and tutorials for building AI infrastructure and systems.
Get weekly updates on trending AI coding tools and projects.