Stars
[NeurIPS 2025] Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
Open Source version of Claude Cowork with 500+ SaaS app integrations
Tools for managing BibTeX bibliographies: automatically update preprints to published versions and filter to only cited references.
An alignment auditing agent capable of quickly exploring alignment hypothesis
Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for training large language models.
LibMoE: A LIBRARY FOR COMPREHENSIVE BENCHMARKING MIXTURE OF EXPERTS IN LARGE LANGUAGE MODELS
Dynamical low rank training for neural networks
A MAD laboratory to improve AI architecture designs 🧪
Open source deep feedback models (DFMs) implemented in PyTorch.
Release data, and checkpoints for "(Almost) Free Modality Stitching of Foundation Models)"
DSPy: The framework for programming—not prompting—language models
GitChameleon, a version-conditioned coding benchmark
A PyTorch native platform for training generative AI models
🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents
Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"
Selective Prompt Anchoring
The PYthoN General UnIt Test geNerator is a test-generation tool for Python
BenchBench is a Python package to evaluate multi-task benchmarks.
Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation and a data preprocessing script.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Efficient Triton Kernels for LLM Training
[CVPR 2022 (oral)] Bongard-HOI for benchmarking few-shot visual reasoning
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation