darrellbest/Qwen3.8-27B-Heretic
image-text-to-text model by darrellbest
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Qwen/Qwen3.8-27B with its refusal behaviour removed by Heretic using Arbitrary-Rank Ablation (ARA), full-weight. bf16, same architecture and parameter count as the original, including its vision encoder, thinking control and the multi-token-prediction weights. Measured by Heretic on mlabonne/harmfulbehaviors (refusals) and mlabonne/harmlessalpaca (KL divergence, the drift in ordinary behaviour), with Heretic's default system prompt and a refusal-marker list that only matches real refusals. The numbers above come from an independent re-evaluation of the exported weights (evaluatemodel), not from the search, and they matched the search exactly. For reference, trohrbaugh/Qwen3.8-27B-heretic-ara reports 0/100 at KL 0.0535 for the same model, so this one lands at the same refusal rate with slightly less drift. ARA, full weight, on attn.oproj and mlp.downproj: Found by a 31-trial search whose first trial was seeded with the parameters published by trohrbaugh (layers 26-56, preserve 0.9432, steer 0.0009, overcorrect 0.5038, 10 neighbours). That seed reproduced on this hardware at 4/100…
Read the full model card ↗ · Preview checked 2026-09-24T07:12:31.386Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
darrellbest/Qwen3.8-27B-Heretic is a image-text-to-text model repository published by darrellbest on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 27,356,728,560
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-24T06:06:57.000Z
- Last modified
- 2026-09-24T06:08:52.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-27B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-24T06:37:32.927Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.