LFM2.5-8B-A1B-heretic-imatrix-GGUF
FadedRedStar/LFM2.5-8B-A1B-heretic-imatrix-GGUF
quantGGUFIQ4_NL
Published metrics
- KL divergence
- 0.024
- Refusals
- 12/100
- Original refusals
- 91/100
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| KL divergence | 0.0239 | | Refusals | 12/100 |
Provenance
- Canonical model
- LiquidAI/LFM2.5-8B-A1B
- Declared parent(s)
- coder3101/LFM2.5-8B-A1B-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-06-27 / 2026-07-10
- Downloads
- 3.3K all time · 147 last 30 days
- License
- other
Refusal rate 12%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.