Template machine learning project using wandb, hydra-zen and submitit on Slurm with Apptainer

MiniMol is a 10M-parameters molecular fingerprinting model pre-trained on >3300 biological and quantum tasks

Papers about graph transformers.

[NeurIPS 2023 AI4Science] "A Transformer Model for Symbolic Regression towards Scientific Discovery"

code for the paper "DiGress: Discrete Denoising diffusion for graph generation"

A concise but complete full-attention transformer with a set of promising experimental features from various papers

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Compositional Linear Algebra

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch

A collection of AWESOME things about Graph-Related LLMs.

NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

Graphium: Scaling molecular GNNs to infinity.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

SignNet and BasisNet

A Graph Neural Network Library in Jax

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

A tiny, simple Java static site generator

Edge representation learning library

List of resources for learning Category Theory

List of resources coming out of Normconf Slack

📝 A nicely formatted LaTeX preprint template

An implementation of local windowed attention for language modeling

Source code for From Stars to Subgraphs (ICLR 2022)