The Well Collection A 15TB collection of physics simulation datasets. • 18 items • Updated Mar 24, 2025 • 41
view article Article makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch May 7, 2024 • 111
view article Article Perceiver IO: a scalable, fully-attentional model that works on any modality Dec 15, 2021 • 14
Running 3.62k The Ultra-Scale Playbook 🌌 3.62k The ultimate guide to training LLM on large GPU Clusters