v2 retraining (readout_v2_paired) fixed the broken clusters — anger, sexual, high_pos, and social_pos all flipped from anti-clustered to positively clustered at deep layers. Validation showed layers 62 and 63 give the best signal; paring the serve-side manifest down to just those two keeps response size tight (~2 KB/token) while keeping the A/B option between the two strongest layers. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| amygdala.rs | ||
| chat.rs | ||
| compare.rs | ||
| context.rs | ||
| learn.rs | ||
| mod.rs | ||
| scroll_pane.rs | ||
| selectable.rs | ||
| subconscious.rs | ||
| thalamus.rs | ||
| unconscious.rs | ||
| widgets.rs | ||