Post #2037912

Posting some light LLM research I've worked on in my spare time. It doesn't count if it's not on your blog! Also nanochat was pretty straight forward to build on top of. Good for model hacking. https://dvshkn.com/blog/2026-05-01-implementing-transformer-model-growth-via-layer-stacking-in-nanochat/ #llm #slm #machinelearning #deeplearning