Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking
DavidAU/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking
finetuneSAFETENSORS
Published metrics
- KL divergence
- 0.0048
- Refusals
- 3/100
- Original refusals
- 97/100
- Heretic version
- —
Published on the model card
Matched snippet
| KL divergence | 0.0048 | | Refusals | 3/100 |
Provenance
- Canonical model
- Qwen/Qwen3-VL-32B-Thinking
- Declared parent(s)
- coder3101/Qwen3-VL-32B-Thinking-heretic-v2
- Classification
- derivative of a Heretic model without its own ablation evidence
- Created / updated
- 2026-01-30 / 2026-01-30
- Downloads
- 1.6K all time · 91 last 30 days
- License
- apache-2.0
Refusal rate 3%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.