9bow

CelebV-HQ

[ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

Eurus

MLX-text-completion-notebook

A simple Jupyter Notebook for learning MLX text-completion fine-tuning!

awslogs

AWS CloudWatch logs for Humans™

awesome-huggingface

🤗 A list of wonderful open-source projects & applications integrated with Hugging Face libraries.

knockknock

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

lightning-whisper-mlx

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

DeepFashion-MultiModal

A large-scale high-quality human dataset with rich multi-modal annotations

podgenai

GPT-4 based informational audiobook/podcast mp3 generator

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

codel

✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.

airbyte

The leading data integration platform for ETL / ELT data pipelines from APIs, databases & files to data warehouses, data lakes & data lakehouses. Both self-hosted and Cloud-hosted.

StyleGAN-Human

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

HDNet_TikTok

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation

MyScaleDB

An open-source, high-performance SQL vector database built on ClickHouse.

long-form-factuality

Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

supervision

We write your reusable computer vision tools. 💜

js-pytorch

A JavaScript library like PyTorch, built from scratch.

baml

BAML is a configuration file format to write typed LLM functions using jinja. Check out the promptfiddle.com playground

imSitu

Support, annotation, evaluation, and baseline models for the imSitu dataset.

Whomane

An open source wearable with camera

Friend

AI wearable necklace

OT_for_big_data

Optimal Transport in the Big Data Era

torchtune

A Native-PyTorch Library for LLM Fine-tuning

MMedLM

The official codes for "Towards Building Multilingual Language Model for Medicine"

jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)