Gemma3-27B-it-vl-GLM-4.7-Uncensored-Heretic-Deep-Reasoning
Greytechai/Gemma3-27B-it-vl-GLM-4.7-Uncensored-Heretic-Deep-Reasoning
finetuneSAFETENSORS
Published metrics
- KL divergence
- 0.070
- Refusals
- 9/100
- Original refusals
- 98/100
- Heretic version
- —
Published on the model card
Matched snippet
| KL divergence | 0.07 | | Refusals | 9/100 |
Provenance
- Canonical model
- google/gemma-3-27b-it
- Declared parent(s)
- coder3101/gemma-3-27b-it-heretic
- Classification
- card identifies this as a finetune of a Heretic model
- Created / updated
- 2026-03-17 / 2026-03-17
- Downloads
- 85 all time · 18 last 30 days
- License
- apache-2.0
Refusal rate 9%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.