Qwen2.5-VL-32B-Instruct-heretic-GGUF
mradermacher/Qwen2.5-VL-32B-Instruct-heretic-GGUF
quantGGUFIQ4_XS
Published metrics
- KL divergence
- 0.412
- Refusals
- 14/100
- Original refusals
- 98/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.4118 | | Refusals | 14/100 |
Provenance
- Canonical model
- Qwen/Qwen2.5-VL-32B-Instruct
- Declared parent(s)
- coder3101/Qwen2.5-VL-32B-Instruct-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-01-18 / 2026-10-08
- Downloads
- 4.2K all time · 649 last 30 days
- License
- apache-2.0
Refusal rate 14%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.