HomeAI Tutorial

nanoKimi

Public

Educational implementation of Kimi-K2 architecture featuring Mixture of Experts, Muon optimizer & Latent Attention. The nanoGPT for next-gen transformers - simple, fast, and educational. Train/finetune Kimi-K2 models with ease!

Creat2025-08-06T05:00:57
Update2025-08-06T05:52:25
0
Stars
0
Stars Increase

Related projects