🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.

The best OSS video generation models, created by Genmo

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Build custom inference engines for models, agents, multi-modal systems, RAG, pipelines and more.

[ICLR 2025] CatVTON is a simple and efficient virtual try-on diffusion model with 1) Lightweight Network (899.06M parameters totally), 2) Parameter-Efficient Training (49.57M parameters trainable) …

LLM101n: Let's build a Storyteller

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

[ICDAR 2023] SelfDocSeg: A self-supervised vision-based approach towards Document Segmentation (Oral)

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

PyTorch native post-training library

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Open-source vector similarity search for Postgres

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A natural language interface for computers

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

OpenChat: Advancing Open-source Language Models with Imperfect Data

A simple toy demo of a local voice assistant with whisper and large language model.

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

A high-throughput and memory-efficient inference and serving engine for LLMs

</> htmx - high power tools for HTML

Implementation of Nougat Neural Optical Understanding for Academic Documents

Automatic Generation of Visualizations and Infographics using Large Language Models

Fast Segment Anything

Document Layout Analysis

Segment Anything in High Quality [NeurIPS 2023]