Energy-based Hallucination detection.

Official Implementation of SIPIT from "Language Models are Injective and Hence Invertible" (ICLR 2026) 🏆

Tiny AI model embedded in NES ROMs to generate character names in-game.

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Official repository of: Attention Sinks in Diffusion Language Models

The best ChatGPT that $100 can buy.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.

Code and checkpoints for our paper "STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning"

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

AISTATS 2025: Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

Geometry processing and machine learning with functional maps.

Code for analyzing and evaluating stellarator plasma boundaries

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗

Repository of the paper "MERGE^3 : efficient evolutionary merging on consumer-grade GPUs" (ICML 2025)

Inference-time scaling for LLMs-as-a-judge.

Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

Flexible library for merging large language models (LLMs) via evolutionary optimization (ACL 2025 Demo).

Generic template to bootstrap your Python project.

Puzzles for learning Triton

🚀 Efficient implementations for emerging model architectures

Fast, Flexible and Portable Structured Generation

LLM KV cache compression made easy

Structured Outputs

Efficient Triton Kernels for LLM Training

Collection of all the papers talking about/relevant to the topic of privacy-preserving LLMs

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models, ICML 2024

This repository collects all relevant resources about interpretability in LLMs