view article Article What We Learned by Reproducing 2,200 papers from ICML abidlabs • 7 days ago • 91
Astronomy Datasets Collection Exoplanets, gravitational waves, pulsars, GRBs, FRBs, quasars, variable stars, and million-source radio/X-ray sky surveys in Parquet. • 104 items • Updated May 16 • 2
The Well Collection A 15TB collection of physics simulation datasets. • 18 items • Updated Mar 24, 2025 • 54
view article Article makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch AviSoori1x • May 7, 2024 • 125
view article Article Perceiver IO: a scalable, fully-attentional model that works on any modality nielsr • Dec 15, 2021 • 17
Running 3.98k The Ultra-Scale Playbook 🌌 3.98k The ultimate guide to training LLM on large GPU Clusters