4 results for tag "moe-training"
A large collection of Claude Code skill templates sponsored by Z.AI, providing ready-to-use development skill configurations across various domains.
A skill from the AI Research Engineering Skills library that teaches AI coding agents how to implement Mixture of Experts (MoE) training for building sparse, efficient large language models.
Enables efficient large-scale model training by implementing Mixture of Experts (MoE) architectures with 5× compute cost reduction and sparse model optimization.