Not training. Transposing rows/columns of matrices to group 128 parameters with ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

syntaxpr 76 days ago | parent | context | favorite | on: Show HN: 1-Bit Bonsai, the First Commercially Viab...

Not training. Transposing rows/columns of matrices to group 128 parameters with similar (shared) scale factor. Qwen-3 model.

MarsIronPI 76 days ago [–]

I'm not sure what you mean. Could you please elaborate?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact