Never forget the resource that helps to close that sales call! Power a real-time speech-to-text agent with retrieval augmented generation based on webscraped customer use-cases.

A unified codebase for finetuning (full, lora) large multimodal models, supporting llava-1.5, qwen-vl, llava-interleave, llava-next-video, phi3-v etc.

Implementation of Paint-with-words with Stable Diffusion : method from eDiff-I that let you generate image from text-labeled segmentation map.

Stable Diffusion Painting

online image editor

Large Model Proxy is designed to make it easy to run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources. It listens on a dedicated port for ea…

EfficientViT is a new family of vision models for efficient high-resolution vision.

An open source implementation of CLIP.

Lightweight, performant, deep table extraction

UniTable: Towards a Unified Table Foundation Model

Implementation of Nougat Neural Optical Understanding for Academic Documents

Code for Text2Performer. Paper: Text2Performer: Text-Driven Human Video Generation

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.

Claude Plus is an advanced AI-powered development assistant that combines the capabilities of Anthropic's Claude AI with a suite of development tools.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

🎙️ Speak with AI - Run locally using ollama or OpenAI - XTTS or OpenAI Speech or ElevenLabs

An app that blurs faces in realtime using VisionCamera, Skia and MLKit 😷

Video anonymization by face detection

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Multi-Aspect Vision Language Pretraining - CVPR2024

[Arxiv-2024] CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation

A collection of resources on applications of multi-modal learning in medical imaging.

"Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA"

BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks

Agent benchmark for medical diagnosis

Interact with your documents using the power of GPT, 100% privately, no data leaks

distributed trainer for LLMs