LFM2.5-8B-A1B-Uncensored
zaakirio/LFM2.5-8B-A1B-Uncensored
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.048
- Refusals
- 0/100
- Original refusals
- 0/100
- Heretic version
- —
Published on the model card
Matched snippet
| Refusals (/100 harmful prompts) | 0 | | KL divergence (harmless prompts) | 0.0481 |
Provenance
- Canonical model
- LiquidAI/LFM2.5-8B-A1B
- Declared parent(s)
- LiquidAI/LFM2.5-8B-A1B
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-06-04 / 2026-06-04
- Downloads
- 206 all time · 65 last 30 days
- License
- other
Refusal rate 0%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.