← back to catalog · registered 2026-09-13 16:56

SOMEHOTMEAL/Gemma-4-12B-Janus-Abliterated-V2-Base_And_GGUF

SOMEHOTMEAL Gemma 12B GGUF multimodal
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 · 30-day
0
Likes
2
Model age
today
created 2026-09-13

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

Quantizations
Q4_K
Tags
transformers safetensors gguf gemma4_unified image-text-to-text mergekit merge conversational arxiv:2311.03099 base_model:culturerevolt/gemma-4-12b-heretic-abliterated base_model:merge:culturerevolt/gemma-4-12b-heretic-abliterated base_model:google/gemma-4-12B-it

Related

Total size
66.7 GB
Files
23
Quantizations
2
Registered
2026-09-13 16:56
Last updated on HF
2026-09-13 16:18

Files by quantization

Q4_K 1 file 15.1 MB
Gemma-4-12B-Janus-Abliterated-V2-Q4_K_M-GGUF.gguf 15.1 MB 8e25ad80 download
Auxiliary files 22 files 66.7 GB
Gemma-4-12B-Janus-Abliterated-V2-f16-GGUF.gguf 22.2 GB 7380415b download
model-00004-of-00005.safetensors 4.64 GB 27ed47f1 download
model-4.safetensors 4.64 GB 27ed47f1 download
model-00003-of-00005.safetensors 4.63 GB 211a1760 download
model-3.safetensors 4.63 GB 211a1760 download
model-00001-of-00005.safetensors 4.55 GB 743e31e9 download
model-1.safetensors 4.55 GB 6295fc3e download
model-00002-of-00005.safetensors 4.55 GB 5f036f7c download
model-2.safetensors 4.55 GB 01d44c0d download
model-00005-of-00005.safetensors 3.84 GB ef2af9fa download
model-5.safetensors 3.84 GB ef2af9fa download
Gemma-4-12B-Janus-Abliterated-V2-Q2_K-GGUF.gguf 15.1 MB 8e25ad80 download
Gemma-4-12B-Janus-Abliterated-V2-Q6_K-GGUF.gguf 15.1 MB 8e25ad80 download
Gemma-4-12B-Janus-Abliterated-V2-Q8_0-GGUF.gguf 15.1 MB acd47c0a download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 64.7 KB 8340abff download
chat_template.jinja 18.6 KB 7d44d305 download
config.json 5.03 KB a62dc29d download
tokenizer_config.json 3.79 KB 358dd210 download
.gitattributes 1.94 KB 376aa447 download
README.md 1.03 KB 7dd9f838 download
mergekit_config.yml 230 B f77d397d download

README current version from Hugging Face


base_model:

  • google/gemma-4-12B-it
  • culturerevolt/gemma-4-12b-heretic-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

Gemma-4-12B-Janus-Abliterated-V2

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

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using google/gemma-4-12B-it as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_linear
base_model: google/gemma-4-12B-it

models:
  - model: culturerevolt/gemma-4-12b-heretic-abliterated
    parameters:
      weight: 0.60
      density: 0.70

dtype: bfloat16
tokenizer_source: base
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.