Qwen2.5-VL-3B-Instruct-heretic-i1-GGUF
mradermacher/Qwen2.5-VL-3B-Instruct-heretic-i1-GGUF
quantGGUFIQ1_M
Published metrics
- KL divergence
- 0.010
- Refusals
- 5/100
- Original refusals
- 99/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.0103 | | Refusals | 5/100 |
Provenance
- Canonical model
- Qwen/Qwen2.5-VL-3B-Instruct
- Declared parent(s)
- coder3101/Qwen2.5-VL-3B-Instruct-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-01-18 / 2026-01-18
- Downloads
- 4.1K all time · 621 last 30 days
- License
- —
Refusal rate 5%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.