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

yamatazen/Shisa-v2-Mistral-Nemo-12B-Abliterated

yamatazen Mistral 12B
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/yamatazen%2FShisa-v2-Mistral-Nemo-12B-Abliterated"
Response includes
  • classification m5
  • files 13
  • hub_downloads_all_time 1,021
  • providers 1
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=yamatazen
All 2 models by yamatazen
 GET/models?family=mistral&method=m5
Sibling mistral models · same method
 GET/methods/m5
What "m5" means · taxonomy
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
M1 Direct removal →
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
How we label → About M5 →
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
1K
184 last 30d - stable
Likes
5
Descendants
3
in 3 direct forks
Model age
17mo ago
created 2025-04-21
Available via
1 provider
featherless-ai
Downloads over time
Now1.1K→from20↑5,540%
04138261.2K20 on Apr 16, 20251.1K on Oct 111.1K on Oct 10Apr '25Jul '25Oct '25JanAprJulOct
Apr 16, 2025 → Oct 11 · 117 snapshots · spans 543 days

Genealogy 3 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.

shisa-ai/shisa-v2-mistral-nemo-12b this lineage
yamatazen/Shisa-v2-Mistral-Nemo-12B-Abliterated↓ 184 3 forks
mradermacher/Shisa-v2-Mistral-Nemo-12B-Abliterated-i1-GGUF↓ 1,874
mradermacher/Shisa-v2-Mistral-Nemo-12B-Abliterated-GGUF↓ 549
yamatazen/Shisa-v2-Mistral-Nemo-12B-Abliterated-Q4_K_M-GGUF↓ 103

Variants by this author 2 formats · 287 downloads combined

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

Metadata

Languages
en ja
Tags
transformers safetensors mistral text-generation mergekit merge abliterated conversational en ja arxiv:2306.01708 base_model:natong19/Mistral-Nemo-Instruct-2407-abliterated

Related

Other by yamatazen
Shisa-v2-Mistral-Nemo-12B-Abliterated-Q4_K_M-GGUF 103
Total size
22.8 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-21 07:03
Source huggingface.co/yamatazen/Shisa-v2-Mistral-Nemo-12B-Abliterated ↗ Base model shisa-ai/shisa-v2-mistral-nemo-12b ↗

Files by quantization

Auxiliary files 13 files 22.8 GB
model-00003-of-00005.safetensors 4.57 GB 7586f93a download
model-00002-of-00005.safetensors 4.57 GB ea311447 download
model-00004-of-00005.safetensors 4.57 GB 89c17740 download
model-00005-of-00005.safetensors 4.57 GB e876b386 download
model-00001-of-00005.safetensors 4.53 GB 0d3ba991 download
tokenizer.json 16.3 MB b0240ce5 download
tokenizer_config.json 177 KB 9a44110b download
model.safetensors.index.json 27.8 KB d95c98c3 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.04 KB 17790a2d download
config.json 618 B 136baddb download
special_tokens_map.json 552 B a782b2f1 download
mergekit_config.yml 231 B 7765ce7a download

README current version from Hugging Face

base_model:

  • shisa-ai/shisa-v2-mistral-nemo-12b
  • natong19/Mistral-Nemo-Instruct-2407-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge
  • abliterated
    language:
  • en
  • ja

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using shisa-ai/shisa-v2-mistral-nemo-12b as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: shisa-ai/shisa-v2-mistral-nemo-12b
models:
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
    parameters:
      density: 1.0
      weight: 1.0
merge_method: ties
dtype: bfloat16
parameters:
  normalize: true

README history 2 versions

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

  1. 2025-04-21Update README.md1b8078a1 KB
    Loading...
  2. 2025-04-21Upload folder using huggingface_hubf3cefa51 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.

Get the app Browse the catalog
Open in Abliteration