LFM2.5-VL-3B-heretic-GGUF
AX1Y2JP/LFM2.5-VL-3B-heretic-GGUF
quantGGUFBF16
Published metrics
- KL divergence
- 0.055
- Refusals
- 6/100
- Original refusals
- 100/100
- Heretic version
- v1.4.0
Published on the model card
Matched snippet
| KL divergence | 0.0553 | | Refusals | 6/100 |
Provenance
- Canonical model
- LiquidAI/LFM2.5-VL-3B
- Declared parent(s)
- LiquidAI/LFM2.5-VL-3B, LiquidAI/LFM2.5-VL-3B-GGUF, LiquidAI/LFM2.5-VL-3B-ONNX, LiquidAI/LFM2.5-VL-3B-MLX-8bit, heretic-org/LFM2.5-VL-3B-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-08-13 / 2026-08-13
- Downloads
- 3.2K all time · 1K last 30 days
- License
- other
Refusal rate 6%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.