kompress-v9 β C3-only (do not use)
This model is a control experiment, not for production. Trained on 97 Qwen2.5-7B labeled pairs with NO generic diversity data. Overfit: heretic 0.921 vs v8's 0.955.
The finding: C3 teacher labels alone are insufficient. Generic multi-domain data acts as necessary regularization. Use kompress-v8 instead.
Series
| Version | heretic | Notes |
|---|---|---|
| v2-base | 0.975 | precision ceiling |
| v4 | 0.943 | self-labels |
| v8 | 0.955 | C3 + generic β use this |
| v9 | 0.921 | C3-only β overfit |
Model tree for PeetPedro/kompress-v9
Base model
answerdotai/ModernBERT-base Adapter
chopratejas/kompress-v2-base