Get the app
← back to catalog · registered 2026-08-22 13:56

Stickmouse/stickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT

Stickmouse 9.4B
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/Stickmouse%2Fstickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT"
Response includes
  • classification m1
  • files 7
  • hub_downloads_all_time 119
  • author_summary 8 models
  • readme_text full
Try next
GET/models?author=Stickmouse
All 8 models by Stickmouse
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
119
12 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-27
Downloads over time
Now122→from0↑0%
045891340 on Jul 29122 on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 days

Variants by this author 2 formats · 121 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
safetensors qwen3_5 abliterated fable opus ornith conversational finetune en base_model:YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated base_model:finetune:YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated license:apache-2.0

Related

Other by Stickmouse
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-Q3_K_M-GGUF 142 stickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT-GGUF 109 Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-Q3_K_S-GGUF 29 gpt-oss-20b-abliterated-claude-opus-4.7-resoning-SFT 0 gpt-oss-20b-abliterated-claude-opus-4.7-resoning-SFT.safetensor-files 0
Total size
17.5 GB
Files
7
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-29 21:02
Source huggingface.co/Stickmouse/stickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT ↗

Files by quantization

Auxiliary files 7 files 17.5 GB
model.safetensors 17.5 GB 1ccf1d7e download
tokenizer.json 19.1 MB 6f32ce20 download
chat_template.jinja 7.42 KB 11be7e25 download
config.json 2.84 KB 091d2e78 download
.gitattributes 1.87 KB 8603d397 download
README.md 1.55 KB b7e6e68a download
tokenizer_config.json 1.14 KB 1d134cd2 download

README current version from Hugging Face

---
license: apache-2.0
language:

  • en
    base_model: YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated
    tags:
  • qwen3_5
  • abliterated
  • fable
  • opus
  • ornith
  • conversational
  • finetune

Stickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT

First-ever finetune done entirely on local hardware. This is Ornith-9B finetuned on a Claude Opus/Fable-distilled dataset — as far as I know, no one else has finetuned Ornith-9B on this kind of dataset before.

Training details

  • Base model: YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated — thanks to YuYu1015 for the abliteration, saved me from having to do it myself.
  • Method: QLoRA
  • Steps: 3546 steps, targeting 2–3 epochs
  • Hardware: Tesla P100 16GB + Titan V 12GB (2016–2018 era cards)
  • Status: Training was interrupted by storage running out at ~71% completion. The released checkpoint reflects that partial run, but still performs well.

This was built on a budget with old hardware — no cloud compute, no big GPU rental. If you're working with even more limited hardware and know how to make it work, I'd love to hear from you.

Planned future finetunes

  • Qwen3.5-9B
  • Attempting Qwen3.6-35B-A3B via QLoRA (ambitious given the hardware, but going to try)

Quantized versions

GGUF quants (f16, Q8_0, Q4_K_M) are available at: Stickmouse/stickmouse-Ornith-1.0-9B-abliterated-Fable-Opus-4.7-Distilled-SFT-GGUF

README history 3 versions

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

  1. 2026-08-01Upload README.md with huggingface_hub89453021.6 KB
    Loading...
  2. 2026-07-27Update README.mde882724264 B
    Loading...
  3. 2026-07-27initial commitaed751128 B
    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.

Get the app Browse the catalog
Open in Abliteration