This is a decensored version of unsloth/Mistral-Small-3.2-24B-Instruct-2506, made using Heretic v1.3.0 with custom ORBA abliteration method
Refusal classification via an LLM judge (Gemma4-12B-it-Heretic).
Performance
| Metric | This model | Original model (unsloth/Mistral-Small-3.2-24B-Instruct-2506) |
|---|---|---|
| KL divergence | 0.0583 | 0 (by definition) |
| Refusals | 1/100 | 98/100 |
- Downloads last month
- 19
Model tree for Sabomako/Mistral-Small-3.2-24B-Instruct-2506-heretic
Base model
mistralai/Mistral-Small-3.1-24B-Base-2503