Tabular Deep Learning Library for PyTorch

GRACE models and gracemaker (as implemented in TensorPotential package)

Turn (almost) any Python command line program into a full GUI application with one line

🏆 A ranked list of awesome atomistic machine learning projects ⚛️🧬💎.

Code for automated fitting of machine learned interatomic potentials.

Distributed High-Performance Symbolic Regression in Julia

🎚️ Open Source Audio Matching and Mastering

Official inference framework for 1-bit LLMs

Blazingly fast LLM inference.

Repository for the Journal Research Data Policy analysis, housing data, code, and the coding framework.

llama3 implementation one matrix multiplication at a time

ParaDiS (Parallel Dislocation Simulator) is a massively parallel Discrete Dislocation Dynamics simulation tool to simulate motion and interaction of large ensembles of dislocations

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

LLM101n: Let's build a Storyteller

A public repository collecting links to state of the art QA and evaluation sets for various ML and LLM applications

Application of Large Language Models (LLM) for computational materials science - visit jan-janssen.com/LangSim

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

A list of Free Software network services and web applications which can be hosted on your own servers

🌐 The Internet OS! Free, Open-Source, and Self-Hostable.

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

This is a repository to discuss, collect and store the requirements for scientific workflow systems

Graph Machine Learning course, Xavier Bresson, 2023

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

yadg: yet another datagram

Machine Learning Engineering Open Book

Question and Answer based on Anything.