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

A Framework of Small-scale Large Multimodal Models

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

FreeGenius AI, an advanced AI assistant that can talk and take multi-step actions. Supports numerous open-source LLMs via Llama.cpp or Ollama or Groq Cloud API, with optional integration with AutoGen agents, OpenAI API, Google Gemini Pro and unlimited plugins.

RestAI is an AIaaS (AI as a Service) open-source platform. Built on top of LlamaIndex, Ollama and HF Pipelines. Supports any public LLM supported by LlamaIndex and any local LLM suported by Ollama. Precise embeddings usage and tuning.

Your all-in-one platform to build and use AI apps effortlessly on your own computer.

Tag manager and captioner for image datasets

A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！

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

Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 40+ HF models, 20+ benchmarks

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

Pheye - a family of efficient small vision-language models

jetson-examples running AI models and applications on NVIDIA Jetson devices with one-line command.

MLX-VLM is a package for running Vision LLMs locally on your Mac using MLX.

⚗️ Llava 13b model repository trained by liuhaotian managed by DVC

⚗️ Zephyr 7b model repository trained by HuggingFaceH4 managed by DVC

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".