Haiderkhan64 / H64LMView on GitHub
249M-param MoE transformer built from scratch in PyTorch. GQA, RoPE, SwiGLU, sparse MoE with 3 aux losses, AMP training loop no Trainer abstractions. Architecture mirrors LLaMA/Mistral/Mixtral decisions, fully inspectable.
19May 22, 2026Updated last month

Alternatives and similar repositories for H64LM

Users that are interested in H64LM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?