Qwen2.5-VL-72B-Instruct-heretic-FP8
anongecko/Qwen2.5-VL-72B-Instruct-heretic-FP8
quantFP8SAFETENSORSFP8
Published metrics
- KL divergence
- 0.016
- Refusals
- 8/100
- Original refusals
- —
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| **Abliteration** | [coder3101/Qwen2.5-VL-72B-Instruct-heretic](https://huggingface.co/coder3101/Qwen2.5-VL-72B-Instruct-heretic) — Heretic v1.2.0 (MPOA), KL divergence 0.0156, refusals 8/100 |
Provenance
- Canonical model
- Qwen/Qwen2.5-VL-72B-Instruct
- Declared parent(s)
- coder3101/Qwen2.5-VL-72B-Instruct-heretic, Qwen/Qwen2.5-VL-72B-Instruct
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-03-20 / 2026-03-20
- Downloads
- 1.2K all time · 83 last 30 days
- License
- other
Refusal rate 8%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.