LFM2.5-1.2B-Instruct-Uncensored
zaakirio/LFM2.5-1.2B-Instruct-Uncensored
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.100
- Refusals
- 5/100
- Original refusals
- 98/100
- Heretic version
- —
Published on the model card
Matched snippet
| Refusals (/100 harmful prompts) | 5 | | KL divergence (harmless prompts) | 0.1003 |
Provenance
- Canonical model
- LiquidAI/LFM2.5-1.2B-Instruct
- Declared parent(s)
- LiquidAI/LFM2.5-1.2B-Instruct
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-06-01 / 2026-06-01
- Downloads
- 1.3K all time · 678 last 30 days
- License
- other
Refusal rate 5%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.