Physics of Language Models, Part 4

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

Experimentation library for comparing fine-tuners for neural sequential predictors.

A user friendly json library written in pure Mojo

Machine Learning library for the emerging Mojo/Python ecosystem

A Lightweight LLM Post-Training Library

A minimal implementation of DeepMind's Genie world model

Post-training with Tinker

Training API and CLI

a categorical deep learning compiler

LaTeX graphics with TikZ, by Packt Publishing

Haskell implementation of open games

This repository contains all the code presented in the online book "Relational Thinking - from Abstractions to Applications".

Lean theorem proving interface which feels like pen-and-paper proofs.

Reinforcement learning for text generation on MLX (Apple Silicon)

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

The absolute trainer to light up AI agents.

Simple and easily configurable grid world environments for reinforcement learning

Provider-agnostic, open-source evaluation infrastructure for language models

A Gym for Agentic LLMs

Mastering Diverse Domains through World Models

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

Data generation engine, sandbox environment and evaluation tools accompanying "ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution".

A Survey of Reinforcement Learning for Large Reasoning Models

MLX: An array framework for Apple silicon

Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support