kkxao/Qwen-Image-2.1-Text-Encoder-Heretic

AI model by kkxao

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

The text encoder of Qwen/Qwen-Image-2.1 (a Qwen3-VL-8B-Instruct) with refusal behaviour removed via Heretic directional ablation. Drop-in replacement for the stock text encoder. Weights are bf16, same shapes, same parameter count — nothing else was changed. Measured by Heretic on mlabonne/harmfulbehaviors (test split) for refusals and mlabonne/harmlessalpaca for KL divergence — i.e. lower refusals and lower distribution shift on benign inputs. Refusal rate and general capability were re-checked with a separate script (different code, different refusal keyword set) rather than trusting the optimiser's own numbers: (e.g. "What is the capital of France?" → "The capital of France is Paris…") Heretic's documented defaults are ntrials = 200, nstartuptrials = 60. A first run with 100/20 was done for comparison: Doubling the search budget nearly halved the refusal rate and cut KL divergence by a third. 100 trials is not enough for this model. If you are abliterating something similar, use the documented…

kkxao/Qwen-Image-2.1-Text-Encoder-Heretic on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-09-22T08:03:16.400Z

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

kkxao/Qwen-Image-2.1-Text-Encoder-Heretic is a task-unspecified model repository published by kkxao on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 8,767,123,696
Architecture: Qwen3VLForConditionalGeneration
License: apache-2.0
Access: Not gated by Hugging Face
Created: 2026-09-22T06:16:44.000Z
Last modified: 2026-09-22T06:16:45.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: Qwen/Qwen3-VL-8B-Instruct

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.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-22T06:37:17.952Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source