The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

GTP engine and self-play learning in Go

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

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

Interact, analyze and structure massive text, image, embedding, audio and video datasets

A curated list of modern Generative Artificial Intelligence projects and services

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

PyGraphistry is a Python library to quickly load, shape, embed, and explore big graphs with the GPU-accelerated Graphistry visual graph analyzer

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

locally hosted web application that allows you to perform various operations on PDF files

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

A curated list of Large Language Model (LLM) Interpretability resources.

ChatGPT web interface using the OpenAI API

[AAAI 2021] Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal

Enhanced ChatGPT Clone: Features OpenAI, GPT-4 Vision, Bing, Anthropic, OpenRouter, PaLM 2, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-…

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

PyGMTSAR

A blazing fast inference solution for text embeddings models

WireHole is a combination of WireGuard, Pi-hole, and Unbound in a docker-compose project with the intent of enabling users to quickly and easily create a personally managed full or split-tunnel Wir…

Efficient Streaming Language Models with Attention Sinks

Whereabouts Ascertainment for Low-lying Detectable Objects. The SOTA in FOSS AI for drones!

Turn expensive prompts into cheap fine-tuned models

This project provides an API with user level access support to transcribe speech to text using a finetuned and processed Whisper ASR model.

Add the ability to receive voice messages as well as text messages to your ChatBot