Llama-3.2-3B-Instruct-heretic-ablitered-uncensored
DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.090
- Refusals
- 12/100
- Original refusals
- 96/100
- Heretic version
- v1.0.1
Published on the model card
Matched snippet
Refusals: 12/100, KL divergence: 0.09 [almost perfect]
Provenance
- Canonical model
- meta-llama/Llama-3.2-3B-Instruct
- Declared parent(s)
- meta-llama/Llama-3.2-3B-Instruct
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2025-11-21 / 2025-11-21
- Downloads
- 5.1K all time · 1.1K last 30 days
- License
- —
Refusal rate 12%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.