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

Mantis2024/Dirty-Shirley-Writer-v0-abliterated

Mantis2024 Gemma 9.2B
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/Mantis2024%2FDirty-Shirley-Writer-v0-abliterated"
Response includes
  • classification m5
  • files 13
  • hub_downloads_all_time 146
  • author_summary 7 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
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 · lifetime
146
24 last 30d - stable
Likes
1
Descendants
4
in 4 direct forks
Model age
18mo ago
created 2025-03-21
Downloads over time
Now154→from15↑927%
86111516815 on Mar 19, 2025154 on Oct 11154 on Oct 8Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 19, 2025 → Oct 11 · 121 snapshots · spans 571 days

Genealogy 4 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.

Variants by this author 2 formats · 60 downloads combined

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

Metadata

Tags
transformers safetensors gemma2 text-generation mergekit merge conversational arxiv:2311.03099 base_model:kayaknights/Gemma-2-Ataraxy-9B-abliterated base_model:merge:kayaknights/Gemma-2-Ataraxy-9B-abliterated base_model:nerdigent/Darkest-muse-v1-lorablated-v2 base_model:merge:nerdigent/Darkest-muse-v1-lorablated-v2

Related

Total size
17.2 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-21 21:40

Files by quantization

Auxiliary files 13 files 17.3 GB
model-00001-of-00004.safetensors 4.65 GB fdf79ed2 download
model-00002-of-00004.safetensors 4.64 GB 55c627dc download
model-00003-of-00004.safetensors 4.61 GB 27a36c46 download
model-00004-of-00004.safetensors 3.32 GB 8d9ab940 download
tokenizer.json 32.8 MB 5f7eee61 download
tokenizer.model 4.04 MB 61a7b147 download
tokenizer_config.json 45.9 KB 9b18de69 download
model.safetensors.index.json 36.3 KB e0d0eac6 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.43 KB 85e7d0b4 download
config.json 891 B 92760978 download
special_tokens_map.json 636 B 8d6368f7 download
mergekit_config.yml 454 B 39feb55a download

README current version from Hugging Face


base_model:

  • nerdigent/Darkest-muse-v1-lorablated-v2
  • nkpz/gemma-2-Ifable-9B-Uncensored-DeLMAT
  • kayaknights/Gemma-2-Ataraxy-9B-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

output-model-directory

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using nerdigent/Darkest-muse-v1-lorablated-v2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nerdigent/Darkest-muse-v1-lorablated-v2
    # No parameters necessary for base model
  - model: kayaknights/Gemma-2-Ataraxy-9B-abliterated
    parameters:
      density: 0.53
      weight: 0.5
  - model: nkpz/gemma-2-Ifable-9B-Uncensored-DeLMAT
    parameters:
      density: 0.53
      weight: 0.5
merge_method: dare_ties
base_model: nerdigent/Darkest-muse-v1-lorablated-v2
parameters:
  int8_mask: true
dtype: bfloat16

README history 1 version

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

  1. 2025-03-21Upload folder using huggingface_hub26c55fc1.4 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