Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

OpenChat: Advancing Open-source Language Models with Imperfect Data

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

React UI + elegant infrastructure for AI Copilots, in-app AI agents, AI chatbots, and AI-powered Textareas 🪁

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

A web crawler and scraper for Rust

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

A realtime serving engine for Data-Intensive Generative AI Applications

Android app for running transformers locally using LLama.cpp & Whisper.cpp

We write your reusable computer vision tools. 💜

Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Explanation to key concepts in ML

Minimalist ML framework for Rust

Modern Android client for Hacker News

It's React, but in Python

QLoRA: Efficient Finetuning of Quantized LLMs

🦜🔗 Build context-aware reasoning applications

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Evaluation of the Open-Assistant language models

Ultralytics YOLO11 🚀

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Home of StarCoder: fine-tuning & inference!