Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Evaluation of LLMs on latest math competitions
A better way of testing, inspecting, and analyzing AI Agent traces.
A syntax-highlighting pager for git, diff, grep, and blame output
A fast + lightweight implementation of the GCG algorithm in PyTorch
Analyze HTTP and DNS requests and create custom DNS records for your subdomain
PostgreSQL vector database extension for building AI applications
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
A repository of Language Model Vulnerabilities and Exposures (LVEs).
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Datasets derived from US census data
The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Discrete Normalizing Flows implemented in PyTorch
Learning Certified Individually Fair Representations
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
The author's officially unofficial PyTorch BigGAN implementation.
A PyTorch implementation of EfficientNet
DL2 is a framework that allows training neural networks with logical constraints over numerical values in the network (e.g. inputs, outputs, weights) and to query networks for inputs fulfilling a …
Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch
An open source python library for scalable Bayesian optimisation.
Open-source simulator for autonomous driving research.
pySMT: A library for SMT formulae manipulation and solving
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.