SkinDeepRESEARCHSteve Seguin

Development diagnostic

Which parts tolerate smaller numbers?

Locate the accuracy loss before attempting another compressed model.

Back to Qwen experiments

Smaller numbers can make a model cheaper to store and run. Our first INT8 conversion broke its answers. This test checks which parts are sensitive to that conversion.

What uses INT8?CorrectNew errors versus float32
Original float3228 / 320
All linear projections14 / 3217
Attention projections only28 / 322
Feed-forward projections only14 / 3217
First 12 layers14 / 3217
Last 12 layers21 / 329
All projections, per-channel weights15 / 3216

Attention-only conversion was less damaging. It introduced 2 errors and corrected 2 others. Matching the total number correct does not mean preserving the answers.

This is a 32-message development diagnostic. All 24 layers still execute. We have not measured a speed benefit or selected this conversion for the demos.

What was inspected?

We compared the final input token’s internal representation after every layer against the same float32 model. Feed-forward conversion caused much larger changes than attention-only conversion on this sample. This narrows down the investigation; it does not prove a single cause or show that all INT8 methods fail.

The classifier, inputs and thresholds stayed fixed. Per-channel conversion was tested too. No message text is copied into these reports.

Method, layer measurements and every outcome