← back to catalog · registered 2026-11-14 18:03

MurakumoKyo/Qwen3.8-27B-Uncensored-LoRA-GGUF

MurakumoKyo 27B GGUF second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/MurakumoKyo%2FQwen3.8-27B-Uncensored-LoRA-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
180
Likes
0
Model age
1w ago
created 2026-11-14

Training datasets

2 of 2 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now 180 → from 0 ↑ 0%
066132198 0 on Nov 14 180 on Nov 22 Nov
Nov 14 → Nov 22 · 9 snapshots · spans 8 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en
Quantizations
BF16 F32
Tags
peft gguf lora abliteration heretic uncensored qwen3.8 text-generation en dataset:mlabonne/harmless_alpaca dataset:mlabonne/harmful_behaviors base_model:PhalaCloud/Qwen3.8-27B-Uncensored-LoRA
Total size
37.2 MB
Files
4
Quantizations
3
Registered
2026-11-14 18:03
Last updated on HF
2026-11-14 17:25

Files by quantization

F32 1 file 24.8 MB
PhalaCloud-Qwen3.8-27B-Uncensored-LoRA_F32.gguf 24.8 MB 5b6c8569 download
BF16 1 file 12.4 MB
PhalaCloud-Qwen3.8-27B-Uncensored-LoRA_BF16.gguf 12.4 MB 3e478de4 download
Auxiliary files 2 files 7.59 KB
README.md 5.94 KB ea2f810c download
.gitattributes 1.65 KB dfe0d5a8 download

README current version from Hugging Face


license: apache-2.0
base_model: PhalaCloud/Qwen3.8-27B-Uncensored-LoRA
base_model_relation: quantized
library_name: peft
pipeline_tag: text-generation
language:

  • en
    datasets:
  • mlabonne/harmless_alpaca
  • mlabonne/harmful_behaviors
    tags:
  • lora
  • abliteration
  • heretic
  • uncensored
  • qwen3.8
  • gguf

Converted Safetensors to GGUF.
All credit goes to PhalaCloud.

===================================================================================

Qwen3.8-27B-Uncensored-LoRA

A 13 MB rank-3 PEFT LoRA over official Qwen3.8-27B, built to remove refusals while retaining the base checkpoint. Serve base and uncensored requests on the same engine, selecting the adapter per request. The BF16 factors target o_proj, out_proj, and down_proj; no merged model is required.

Evaluation

Measured on H200 with official Qwen3.8-27B-FP8, FP8 KV cache, and EAGLE. Stock is the same serving base without runtime LoRA. Refusal counts include full and partial refusals; off/on means thinking disabled/enabled.

Evaluation Stock Adapter
StrongREJECT refusals, primary judge (off / on) 59/60 / 60/60 0/60 / 0/60
StrongREJECT refusals, second judge (off / on) 60/60 / 60/60 4/60 / 1/60
XSTest safe refusals, primary (off / on) 3/50 / 2/50 0/49 / 0/49 valid
Product-task refusals, primary (off / on) 2/30 / 3/30 0/30 / 0/30
GSM8K flexible-extract, thinking off 1,271/1,319 (96.36%) 1,275/1,319 (96.66%; +0.30pp)
IFEval prompt-level strict, thinking off 446/541 (82.44%) 442/541 (81.70%; -0.74pp)
Capability templates 44 stock-passing templates 44/44 pass
Reasoning-on tool calling, broken / 300 rounds 6/300 1/300

Quality generation used a 4,096-token cap; adapter empty/truncated answers were 1/1,319 on GSM8K and 6/541 on IFEval. All 52 templates were exercised; the 44 stock-passing templates define the regression comparison. Tool calling used the qwen3_coder parser.

Refusals were labeled by two independent LLM judges using the same rubric on the same answers. Automated labels are not human ground truth.

Serving

Tested image: ghcr.io/phala-network/sglang:phala-v0.5.21-10@sha256:c89968920dc5facaa54ff735e2a431b3b6dac51adde8c6424badc58fe03d6c13.
Serving base: Qwen/Qwen3.8-27B-FP8 revision 017b9c7af6b5689d5dd426a76e0bc077eb5ca20a.

Place the two adapter files in /adapters/unc-r3-1abf13b2. Add these flags to the pinned base serving profile:

--served-model-name qwen/qwen3.8-27b \
--reasoning-parser qwen3 --tool-call-parser qwen3_coder \
--enable-lora --lora-strict-loading \
--lora-paths unc-r3-1abf13b2=/adapters/unc-r3-1abf13b2 \
--max-lora-rank 3 --max-loras-per-batch 2 --max-loaded-loras 2

Target modules are inferred from adapter_config.json; strict loading rejects unmatched weights. Omit the explicit target-module flag: this image's CLI rejects out_proj even though the model supports it through inference. vLLM is untested for this adapter.

Select the adapter with the full base:adapter model name:

{
  "model": "qwen/qwen3.8-27b:unc-r3-1abf13b2",
  "messages": [{"role": "user", "content": "Write a short fictional dialogue."}],
  "max_tokens": 512,
  "chat_template_kwargs": {"enable_thinking": false}
}

Use qwen/qwen3.8-27b for base requests; a bare adapter alias can silently select the base.

Verification

1abf13b2191c9973a4dc4d978448512d3ce2efabfd1e671edd5956b6aebfa5ac  adapter_model.safetensors
d716fa478316e84ed9d08875db621c84ec377145297bbb834a338ac5ae0de285  adapter_config.json

From the directory containing both files and SHA256SUMS:

sha256sum -c SHA256SUMS

How it was built

Heretic v1.3.0 used official Qwen3.8-27B with NF4 loading/BF16 compute, rank 3, full row normalization, and an orthogonalized direction.
Seed 20261108, batch 16, thinking off, 100-token construction cap; 200-trial budget, 60 startup trials, 7,200-second limit (85 completed).
Selection minimized construction refusals among Pareto trials with KL <= 0.22, then KL and trial index; trial 61 won (KL 0.1080). Evaluation scores did not select the winner.
Native factors were retained before merging and explicitly cast to BF16. Exact normalized evaluation overlaps were excluded; semantic/task-family overlap remains possible.

Construction dataset (pinned revision) Train / test Upstream license
mlabonne/harmless_alpaca 400 / 100 Stanford Alpaca-derived, CC BY-NC 4.0
mlabonne/harmful_behaviors 400 / 96 AdvBench-derived, MIT upstream

License and intended use

The adapter is released under Apache-2.0 (LICENSE). This license covers the adapter weights only and does not grant rights in the datasets used to construct it.

mlabonne/harmless_alpaca derives from Stanford Alpaca, whose data is licensed CC BY-NC 4.0 with research-only guidance for trained models. Users are responsible for complying with the terms of the upstream datasets.

Reducing refusals does not establish accuracy or safety: outputs may be harmful, fabricated, or unreliable. Other runtimes, quantizations, hardware, and serving profiles require fresh evaluation.

Credits

Phala; Qwen for the base model; Philipp Emanuel Weidmann and contributors for Heretic; Maxime Labonne for the dataset mirrors; the Stanford Alpaca and AdvBench authors for the upstream data. See NOTICE.

README history 8 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-14 Update README.md d56f70e 5.9 KB
    Loading...
  2. 2026-11-14 Update README.md b1be4a1 5.9 KB
    Loading...
  3. 2026-11-14 Update README.md b9ef948 5.8 KB
    Loading...
  4. 2026-11-14 Update README.md 38aab0d 5.8 KB
    Loading...
  5. 2026-11-14 Update README.md 0ab030b 5.8 KB
    Loading...
  6. 2026-11-14 Update README.md fe79f4a 5.8 KB
    Loading...
  7. 2026-11-14 Upload README.md 02deb8b 5.5 KB
    Loading...
  8. 2026-11-14 Create README.md f7159f5 4.9 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration