Downloads · 30 days
29
19% of all-time downloads
Zynerji/Ektome-Qwen3-VL-8Bi-PristinelyUncensored
Ektome-Qwen3-VL-8Bi-PristinelyUncensored is a image-text-to-text model from Zynerji. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Uncensored vision-language model. No capability certificate has been issued for it yet, so no retention claim is made here.
Downloads · 30 days
29
19% of all-time downloads
All-time downloads
155
Public
Parameters
8.8B
17.5 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors17.5 GB · 100%
From the Hugging Face model README
Uncensored vision-language model. No capability certificate has been issued for it yet, so no retention claim is made here.
compliance on harmful prompts 0.64 -> 1.00, MMLU-val 0.730 -> 0.730 (dcap +0.000) versus pristine
Qwen/Qwen3-VL-8B-Instruct.
A single-step, training-free, norm-preserving low-rank excision of the refusal-specific
subspace, applied to the language decoder only. The vision tower is untouched: the
residual-write targets match 72 tensors under model.language_model and zero under
model.visual, so image understanding is inherited unchanged from the base model.
Extraction depth was selected by an automated sweep that scores capability as well as compliance at each qualifying depth, rather than stopping at the first depth that uncensors. Eight depths reached compliance 1.000; the shallowest was not the cheapest.
| model | MMLU-val (n=200) | compliance on harmful |
|---|---|---|
pristine Qwen3-VL-8B-Instruct | 0.730 | 0.64 |
| this model | 0.730 | 1.00 |
These are point estimates with no confidence interval. MMLU-val at n=200 has SE ~0.03, so a difference of this size is inside the noise floor — it is evidence of no large loss, not proof of exact preservation.
No n=2800 paired non-inferiority certificate has been run for this model. Do not treat the receipt above as a capability guarantee.
Uncensored by construction: it will not refuse, and the operator is accountable for its use. Compliance is measured with a judge-free keyword classifier, which evasive phrasing can fool.