decision-models

1 post connected to this tag.

Oct 23, 2026

From LM Heads to Decision Heads: How Clef-Style Models Work and Train

A visual, measured breakdown of language-model heads, fixed classifiers, and Clef-style decision heads, including our Qwen3-0.6B Unsloth training run and its limits.

Read post →

Get my rants delivered to your inbox

I will send new posts as and when I write. No fixed cadence, just engineering notes, rants, and things I am thinking through.

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

Work With Us / Antshiv Robotics

See engineering services

decision-models

From LM Heads to Decision Heads: How Clef-Style Models Work and Train

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

ShivasNotes

Read

Support

Owned by Antshiv Robotics

Published with Antsand

From LM Heads to Decision Heads: How Clef-Style Models Work and Train

Subscribe

Subscribe to emails from Anthony

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

ShivasNotes

Read

Support

Owned by Antshiv Robotics

Published with Antsand