Downloads · 30 days
13
29% of all-time downloads
Zynerji/Ektome-Qwen3.5-9B-PristinelyUncensored-frac085
Ektome-Qwen3.5-9B-PristinelyUncensored-frac085 is a machine learning model from Zynerji. Use it for the machine learning 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.
An alternative to the default build, excised at layerfrac=0.85 instead of 0.90. It trades a little capability for full compliance.
Downloads · 30 days
13
29% of all-time downloads
All-time downloads
45
Public
Parameters
9.4B
18.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors18.8 GB · 100%
From the Hugging Face model README
An alternative to
the default build,
excised at layer_frac=0.85 instead of 0.90. It trades a little capability for full compliance.
| pristine | frac 0.85 (this) | frac 0.90 (default) | |
|---|---|---|---|
| compliance (n=100) | 0.000 | 1.000 | 0.950 |
| MMLU-val (n=400) | 0.7925 | 0.775 | 0.795 |
| dcap | — | −0.0175 | +0.003 |
Vision tower retained. 64 residual-write matrices edited.
This configuration sits on the capability threshold, and its pass/fail verdict is not reproducible. Two runs of the identical config measured dcap −0.022 (fails, SE 0.020) and −0.0175 (passes). The capability difference from frac 0.90 is real and reproducible at roughly 0.02 MMLU; which side of the gate it lands on is decided by sampling noise at n=400.
So the choice between this and the default is a judgement, not a gate outcome: +0.05 compliance for ~0.02 MMLU. The default build is the conservative pick and is the one to use if you have no specific reason to prefer this.
-NF4
— ~7.4 GB, vision retained, compliance 1.000, MMLU 0.770-GGUF
— Q4_K_M + mmproj (required for vision)GPTQ is not possible here either: Gated DeltaNet in_proj emits 32 out-features and Marlin
needs a multiple of 64.
Ektomē: a rank-1 projected (orthogonalised against the harmless mean), norm-preserving
excision of the refusal direction from residual-write matrices (o_proj, out_proj,
down_proj). Zero training, zero fine-tuning, zero distillation — the delta is a linear
weight edit derived from activations. A configuration ships only if compliance clears target
and capability holds (dcap ≥ −SE) and generation quality holds (no code-switching,
degeneration, or instruction-following loss).