Llama-3.3-70B-Instruct-SOM-MPOA
0xA50C1A1/Llama-3.3-70B-Instruct-SOM-MPOA
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.049
- Refusals
- 5/100
- Original refusals
- 84/100
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| KL divergence | 0.0494 | | Refusals | 5/100 |
Provenance
- Canonical model
- unsloth/Llama-3.3-70B-Instruct
- Declared parent(s)
- unsloth/Llama-3.3-70B-Instruct
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-04-20 / 2026-04-20
- Downloads
- 3.9K all time · 20 last 30 days
- License
- llama3.3
Refusal rate 5%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.