Inspect: A framework for large language model evaluations

Official inference framework for 1-bit LLMs

Using repe for guarding your LLM

A modular graph-based Retrieval-Augmented Generation (RAG) system

ObjectRL: An Object-Oriented Reinforcement Learning Codebase

Isolating Culture Neurons in Multilingual Large Language Models

Language model training framework in modern Pytorch

Master's thesis on reinforcement fine-tuning LLMs with GRPO to generate Prolog code for symbolic reasoning and inference

Datasheets and descriptive stats for data used for the DFM project.

Training Sparse Autoencoders on Language Models

Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem

The AI coding agent built for the terminal.

Interroger à l'aveugle deux modèles de langage conversationnels sur des tâches exprimées en français et comparer les résultats.

A simple and elegant theme for Jekyll and GitHub Pages.

timing context manager for typical ML training

GitHub's official MCP Server

Superfast AI decision making and intelligent processing of multi-modal data.

Mechanistic interpretibility for quantized LLMs – a work in progress

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

The website for Danish Foundation Models, a project for training foundational Danish language model.

The robust European language model benchmark.

This repository contains the Hugging Face Agents Course.

Decouple Torch Network-Aware Training on Interlinked Online Nodes

See Through Your Models

awesome papers in LLM interpretability

This repository collects all relevant resources about interpretability in LLMs

Jekyll theme inspired by Swiss design

Minima is a one-size-fits-all Jekyll theme for writers.