LFM2.5-1.2B-Thinking-heretic
saidutta69/LFM2.5-1.2B-Thinking-heretic
hereticGGUFSAFETENSORSF16
Published metrics
- KL divergence
- 0.0005
- Refusals
- 10/100
- Original refusals
- 98/100
- Heretic version
- v1.4.0
Published on the model card
Matched snippet
| KL divergence | 0.0005 | | Refusals | 10/100 |
Provenance
- Canonical model
- LiquidAI/LFM2.5-1.2B-Thinking
- Declared parent(s)
- LiquidAI/LFM2.5-1.2B-Thinking
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-10-15 / 2026-10-15
- Downloads
- 714 all time · 714 last 30 days
- License
- other
Refusal rate 10%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.