Mistral-7B-Instruct-v0.3-heretic
paoloronco/Mistral-7B-Instruct-v0.3-heretic
hereticLORASAFETENSORS
Published metrics
- KL divergence
- 0.061
- Refusals
- 4/100
- Original refusals
- —
- Heretic version
- v1.3.0
Published on the model card
Matched snippet
| KL divergence | 0.0606 | | Refusals out of 100 prompts | 4/100 |
Provenance
- Canonical model
- mistralai/Mistral-7B-Instruct-v0.3
- Declared parent(s)
- mistralai/Mistral-7B-Instruct-v0.3
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-05-27 / 2026-05-27
- Downloads
- 181 all time · 26 last 30 days
- License
- apache-2.0
Refusal rate 4%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.