Qwen3.5-27B-ultra-uncensored-heretic-v1
llmfan46/Qwen3.5-27B-ultra-uncensored-heretic-v1
hereticSAFETENSORS
Published metrics
- KL divergence
- 0.030
- Refusals
- 3/100
- Original refusals
- 95/100
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| KL divergence | 0.0301 | | Refusals | 3/100 |
Provenance
- Canonical model
- Qwen/Qwen3.5-27B
- Declared parent(s)
- Qwen/Qwen3.5-27B
- Classification
- card states the weights were abliterated with Heretic
- Created / updated
- 2026-02-28 / 2026-03-31
- Downloads
- 9.2K all time · 470 last 30 days
- License
- apache-2.0
Published benchmarks
Copied from the model card. These never affect the ranking.
| Metric | This model | Original | Delta |
|---|---|---|---|
| MMLU | 0.8456 | — | — |
Refusal rate 3%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.