Stars
Build, enrich, and transform datasets using AI models with no code
Renderer for the harmony response format to be used with gpt-oss
A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗
Everything about the SmolLM and SmolVLM family of models
ScreenSuite - The most comprehensive benchmarking suite for GUI Agents!
A repository to unravel the language of GPUs, making their kernel conversations easy to understand
Build compute kernels and load them from the Hub.
This repository contains the Hugging Face Agents Course.
Fully open reproduction of DeepSeek-R1
Minimalistic 4D-parallelism distributed training framework for education purpose
Recipes to scale inference-time compute of open models
A course on aligning smol models.
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Build local voice agents with open-source models
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Scripts to download and assemble printable versions of Roche's famous biochemical pathways poster
Easily embed, cluster and semantically label text datasets
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Minimalistic large language model 3D-parallelism training
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
A blazing fast inference solution for text embeddings models
Robust recipes to align language models with human and AI preferences
LLM powered development for VSCode