Downloads · 30 days
195
44% of all-time downloads
msuiche/Qwen3.8-27B-abliterated-cyber-GLP-49
Qwen3.8-27B-abliterated-cyber-GLP-49 is a machine learning model from msuiche. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Two small files that remove refusal behaviour from Qwen/Qwen3.8-27B without redistributing the model. The base checkpoint stays byte-identical.
Downloads · 30 days
195
44% of all-time downloads
All-time downloads
439
Public
Repo size
15.8 MB
Likes
6
Public
Click a slice to open those files.
.safetensors8.6 MB · 79%
From the Hugging Face model README
Two small files that remove refusal behaviour from Qwen/Qwen3.8-27B without
redistributing the model. The base checkpoint stays byte-identical.
| file | size | needs |
|---|---|---|
adapter_model.safetensors + adapter_config.json | 8.6 MB | stock peft, verified |
Qwen3.8-27B-abliterated-cyber-GLP-49-L10-58-a1.gguf | 1.0 MB | a runtime that understands glp.mode. Experimental |
Qwen3.8-27B-abliterated-cyber-GLP-63-L1-63-a1.gguf (pooled variant, matches the LoRA's layer span) | 1.3 MB | same |
For comparison, published abliterations of this same model are 30.9 GB and 20.6 GB.
Start with the LoRA. It works on stock tooling. The GGUF is here because on architectures where a LoRA is impossible the projective format is the only route, and this is the reference implementation of it.
Measured on Qwen/Qwen3.8-27B at revision 1d4bf0f2ff60, greedy decoding, 300 new
tokens, three-way scored with a degeneracy guard.
| suite | unmodified | LoRA | control vector |
|---|---|---|---|
| general refusal (n=32, in-sample) | 3.1 % | 81.2 % | 84.4 % |
| harmless control (n=32, held out) | 100 % | 100 % | 100 % |
| offensive-security holdout (n=32, private) | 12.5 % | 100 % | 96.9 % |
| capability probe | 11/12 | 11/12 | 12/12 |
Delivery, not refusal rate, so higher is better. The harmless control is held out of the derivation entirely. The security suite contains no content resembling the derivation contrast.
Over-refusal is 0 points on the held-out control. An earlier in-sample control read −15.6, which is a stricter bound by construction: the direction was fitted to separate the harmful set from that control, so it sits on the decision boundary.
from transformers import AutoModelForImageTextToText, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3.8-27B"
model = AutoModelForImageTextToText.from_pretrained(base, dtype="bfloat16", device_map="cuda:0")
model = PeftModel.from_pretrained(model, "msuiche/Qwen3.8-27B-abliterated-cyber-GLP-49")
tok = AutoTokenizer.from_pretrained(base)
merge_and_unload() bakes it in if you want a merged checkpoint.
lora_alpha / r = 1.0, and α is already baked into lora_A. Raising it does not
strengthen removal. It reflects the component instead of removing it:
α = 1 h·d̂ → 0 the component is removed
α = 2 h·d̂ → −(h·d̂) the component is REFLECTED
At α=2 this model refused 37.5 % of entirely harmless prompts (sourdough, birdwatching, repotting a houseplant) with factual capability perfectly intact. That is the same vector installing the behaviour rather than removing it.
This adapter covers layers 1 to 63. You do not have to use all of them, and coverage is the safe dial where α is not. Measured on a 43-layer model, same direction and same α, varying only how many layers were touched:
| layers steered | refusal remaining |
|---|---|
| 6 | 18.0 % |
| 16 | 3.8 % |
| 29 | 0.0 % |
Partial coverage does less of the same thing. Raising α does something different and dangerous. So to tune strength, subset the layers and leave α at 1.
That also makes targeted work possible. The direction is applied per layer, so you can confine it to a depth range and ask what that range contributes, rather than treating the model as one switch. Two cautions from doing this:
To build a narrower adapter, re-run the derivation with the span you want. Editing this
file's tensor list is equivalent, since each layer's lora_A/lora_B pair is
independent.
lora_A = −α·d̂ᵀW is computed once from the bf16 weights. Load it onto a quantised copy
of the same checkpoint and the error enters only through d̂ᵀ(W − W_q)x, which is the
quantisation noise projected onto a single direction and therefore suppressed by about
1/√5120:
| base | weight error | error in the projection |
|---|---|---|
| bf16 | 0 % | 0.00 % |
| int8 | 0.67 % | 0.61 % |
| int4 | 12.0 % | 3.57 % |
At int4 the weights are twelve percent wrong and the intervention is still ninety-six percent correct. One adapter should therefore cover the FP8, NVFP4, int8, int4 and GGUF re-encodings of this checkpoint, rather than each needing its own abliterated upload.
This is measured on the arithmetic, not on behaviour. Delivery on a quantised base has not been benchmarked.
It is a rank-1 LoRA computed in closed form, not trained. No optimiser, no training data:
B = d̂ a direction in the residual stream
A = −α · d̂ᵀW one matrix-vector product against the base weights
d̂ comes from a difference of means over 32+32 prompts at the last prompt token, with
the top 0.5 % of dimensions masked. This checkpoint has a massive-activation dimension
running 75 to 434 times the median, which otherwise dominates the estimate. Applied at
both residual writers across layers 1 to 63: 126 matrices, ‖ΔW‖/‖W‖ mean 0.0143.
Checkpoint-bound. lora_A contains W, so this file is valid for
Qwen/Qwen3.8-27B at revision 1d4bf0f2ff60 and its re-quantisations. It is not
portable to another model or another size. The method transfers to any dense model.
The file does not.
Baked form ≠ runtime steering. This adapter projects each residual writer's output, which by linearity equals projecting each layer's new contributions at α. A d̂-component already in the incoming stream (embeddings, an uncovered writer) passes through, where a runtime hook on the accumulated stream removes it regardless of origin. Close in practice here because writers re-inject the direction every layer, but not bit-identical — treat the adapter as the portable/troubleshooting form and the GGUF + runtime hook as the reference behavior.
peft attaches an adapter to layer 0. target_modules is matched by suffix, so peft
hooks layer 0 as well, which this file deliberately excludes. It is inert only because
peft zero-initialises B, verified here as exactly zero contribution and zero weight
change after merge. That is a property of peft's defaults, not of this file, and it
matters because steering layer 0 silences the model.
Untested: vLLM and llama.cpp. Both should work, since vLLM permits LoRA on any
linear layer and llama.cpp has the qwen35 architecture, but neither has been loaded.
The GGUF needs a patched runtime. It declares glp.mode = project, meaning
h ← h − α(h·d̂)d̂. llama.cpp's built-in control vectors are additive, h ← h + s·d̂,
which is a different operation: it pushes every token along the axis instead of removing
the component, and it fails silently. A reader that does not understand glp.mode
must refuse the file rather than fall back to adding. Support lives in our llama.cpp fork (currently private).
The harness scores REFUSE / DEFLECT / COMPLY plus a degeneracy guard. It does not yet separate a fourth state we found: the steered model rejecting a question's premise and then answering in full. "I cannot provide instructions on how to make sourdough rise improperly…", followed by 1,300 characters of correct instructions. Those score as refusals, so over-refusal figures here are an upper bound.
base Qwen/Qwen3.8-27B @ 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
contrast 32 harmful / 32 form-matched harmless, cross-domain
estimator difference of means, 0.5% massive-activation masked, pooled
hook post-layer residual, layers 1-63, alpha = 1
gguf sha256 bd34cefca94ae09f27935b9b881924d17a8b0dd87859969ad8dbf5c7217ccd07
lora sha256 32980b48abc4018255a1ee5a5c2fbd55ee110132482dd18c29b86e0b150334f7
A third party's direction, recovered from published weights by SVD and run through the same harness, scores 90.6 / 100 / 100, which is better than this one on general refusal. That is recorded because it is true, and because the gap is the contrast rather than the method: their prompt sets pushed through this pipeline reproduce their result.
Security research and evaluation. Measuring how robustly a capability is gated requires being able to switch the gate off and observe what changes, and that work is only possible on open-weight models.
Three measurements landed since this card was written. Nothing changes the direction or the delivery numbers above; they change how you should serve it.
enable_thinking=false) or grammar-constrain the output
(JSON schema / guided decoding) — structured output restores clean stops
in our tests. For short-form security Q&A (this vector's purpose), no
change needed. If you need a baked artifact with trained-in termination
rather than a runtime vector, his SFT-class card above is the current
best-in-class alternative — different trade (weights vs 8.6 MB adapter).