Stars
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
RelBench: Relational Deep Learning Benchmark
Fine-tune mistral-7B on 3090s, a100s, h100s
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)
GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
Associated Repository for "Translation between Molecules and Natural Language"
An open-source platform for developing protein models beyond AlphaFold.
Rapid experimentation and scaling of deep learning models on molecular and crystal graphs.
Official implementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".
EVA Series: Visual Representation Fantasies from BAAI
A simple minimal implementation of Reversible Vision Transformers
A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.
This is the official repo for the paper "Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions", presented at NeurIPS 2022.
[ICLR 2021] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (https://arxiv.org/abs/2010.13993)
PyTorch reimplementation of "A simple, efficient and scalable contrastive masked autoencoder for learning visual representations".
Recipe for a General, Powerful, Scalable Graph Transformer
[NeurIPS 2020] "Graph Contrastive Learning with Augmentations" by Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen
Implementation of "Learning Combinatorial Optimization Algorithms over Graphs"
A PyTorch implementation of The ICLR 2019 paper "Invariant and Equivariant Graph Networks" by Haggai Maron, Heli Ben-Hamu, Nadav Shamir and Yaron Lipman https://openreview.net/forum?id=Syx72jC9tm. …
FFCV: Fast Forward Computer Vision (and other ML workloads!)
An implementation for Karger Minimum cut algorithem
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Graph Transformer Architecture. Source code for "A Generalization of Transformer Networks to Graphs", DLG-AAAI'21.