Environments for LLM Reinforcement Learning

Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase

Official implementation of the ICLR'25 paper "QERA: an Analytical Framework for Quantization Error Reconstruction".

VisualWebArena is a benchmark for multimodal agents.

Chat Templates for 🤗 HuggingFace Large Language Models

Adaptive Experimentation Platform

Framework and Language for Neurosymbolic Programming.

causalimages: An R package for performing causal inference with image and image sequence data

Automatic Input Generation System for Android Apps

A System for Debloating C/C++ Programs