gemma-3-270m-it-heretic-refusal-plugin-trial99-test
0utsideness/gemma-3-270m-it-heretic-refusal-plugin-trial99-test
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.398
- Refusals
- 25/100
- Original refusals
- 98/100
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| Refusals | 25/100 | | KL divergence | 0.3984 |
Provenance
- Canonical model
- google/gemma-3-270m-it
- Declared parent(s)
- google/gemma-3-270m-it, google/gemma-3-270m
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-02-22 / 2026-02-22
- Downloads
- 110 all time · 19 last 30 days
- License
- gemma
Refusal rate 25%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.