Automatically extract executable programs from pruned mechanistic circuits, extending OpenAI's Sparse Circuits

Scalable data pre processing and curation toolkit for LLMs

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

SkyRL: A Modular Full-stack RL Library for LLMs

open-source healthcare ai

A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗

slime is an LLM post-training framework for RL Scaling.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

InfraScale: How many GPU do I need for LLM inference?

Our library for RL environments + evals

Lightweight coding agent that runs in your terminal

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

The glamourous AI coding agent for your favourite terminal 💘

Late Interaction Models Training & Retrieval

BioMCP: Biomedical Model Context Protocol

The simplest, fastest repository for training/finetuning small-sized VLMs.

Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts) @ NAACL 2024

A distributed storage benchmark for file systems, object stores & block devices with support for GPUs

Toolkit for linearizing PDFs for LLM datasets/training

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Async RL Training at Scale

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

This package is a collection of datasets for evaluating AI Models in the context of Home Assistant.

A Python tool to evaluate the performance of VLM on the medical domain.