Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.

Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps

Inference server for MioTTS, a lightweight and fast LLM-based TTS model.

A framework for few-shot evaluation of language models.

SGLang is a high-performance serving framework for large language models and multimodal models.

Ongoing research training transformer models at scale

Renderer for the harmony response format to be used with gpt-oss

Docker Model Runner

Pure Rust engine for BitNet LLMs — Conversion, Inference, Training and Research. With streaming and GPU/CPU support

250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

🚀 Efficient implementations for emerging model architectures

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

All information and news with respect to Falcon-H1 series

Lightweight toolkit package to train and fine-tune 1.58bit Language models

Build compute kernels and load them from the Hub.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Automatic evals for LLMs

A version manager for neovim

An extremely fast Python linter and code formatter, written in Rust.

Segment Anything for Microscopy

Minimalistic 4D-parallelism distributed training framework for education purpose

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

MLX: An array framework for Apple silicon

Official inference framework for 1-bit LLMs

Baichuan-Omni: Towards Capable Open-source Omni-modal LLM 🌊

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!