Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

MLX: An array framework for Apple silicon

Go ahead and axolotl questions

Black-box extraction of Finite-State Machines from RNNs.

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

A python Linear Programming API

Machine Learning framework for Sofa

a multi-task reinforcement learning environment compatible with OpenAI gym

Gin provides a lightweight configuration framework for Python

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Google Research

Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

Working directory for dynamics learning for experimental robots.

Library for Model Based RL

Source code for the paper: "Neural Methods for Logical Reasoning over Knowledge Graphs"

Neural Collaborative Reasoning

Can Neural Networks Crack Sudoku?

Multi-Hop Logical Reasoning in Knowledge Graphs

Benchmarking the Spectrum of Agent Capabilities

ML Collections is a library of Python Collections designed for ML use cases.

Animation engine for explanatory math videos

Python bindings for FFmpeg - with complex filtering support

Mingus is a music package for Python

What the f*ck Python? 😱

A simple and highly efficient RTS-game-inspired environment for reinforcement learning