A playbook for systematically maximizing the performance of deep learning models.

🤗 smolagents: a barebones library for agents that think in python code.

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

Inference and training library for high-quality TTS models.

verl: Volcano Engine Reinforcement Learning for LLMs

first base model for full-duplex conversational audio

Fast and accurate automatic speech recognition (ASR) for edge devices

Deduplicating archiver with compression and authenticated encryption.

The AI-native proxy server for agents. Arch handles the pesky heavy lifting in building agentic apps - routing prompts to agents or specific tools, clarifying input, unifying access and observabili…

Go ahead and axolotl questions

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

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

Scalable toolkit for efficient model alignment

Explore careers based on your interests and skills with AI

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Open Source realtime backend in 1 file

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

Training LLMs with QLoRA + FSDP

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

A series of large language models trained from scratch by developers @01-ai

A pandoc LaTeX template to convert markdown files to PDF or LaTeX.

Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

TorchCFM: a Conditional Flow Matching library

PyTorch code and models for V-JEPA self-supervised learning from video.

Curated list of useful LLM / Analytics / Datascience resources

A machine learning software for extracting information from scholarly documents

📄 ⚙️ ETL processes for medical and scientific papers