← back to catalog · registered 2026-09-17 20:56

enkato64bit/SuperGemma-4-12b-abliterated

enkato64bit Gemma 12B multimodal
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-17

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 ko
Tags
transformers safetensors gemma4_unified image-text-to-text gemma4 multimodal supertune abliterated refusal-reduction post-training korean code

Related

Total size
22.3 GB
Files
10
Quantizations
1
Registered
2026-09-17 20:56
Last updated on HF
2026-09-17 20:27

Files by quantization

Auxiliary files 10 files 22.3 GB
model.safetensors 22.3 GB e67b7e6c download
tokenizer.json 30.7 MB 78c7e081 download
chat_template.jinja 28.3 KB eceb4aaa download
config.json 4.24 KB 02136bf8 download
generation_config.json 4.01 KB f28cf89e download
README.md 3.51 KB c715ded0 download
tokenizer_config.json 2.84 KB df65a194 download
processor_config.json 1.35 KB b889adcd download
fuse_summary.json 461 B 57c8df11 download
.gitattributes 269 B f5c8bf19 download

README current version from Hugging Face


license: apache-2.0
base_model: google/gemma-4-12B-it
library_name: transformers
pipeline_tag: text-generation
tags:

  • gemma4
  • multimodal
  • supertune
  • abliterated
  • refusal-reduction
  • post-training
  • korean
  • code
    language:
  • en
  • ko

SuperGemma-4-12b-abliterated

SuperGemma-4-12b-abliterated is a fused 12B checkpoint derived from google/gemma-4-12B-it.

The release combines two post-training stages:

  1. Abliteration pass - a weight-space refusal-direction pass designed to suppress unnecessary refusal behavior and improve direct task completion.
  2. Supertune post-training - targeted post-training for instruction following, coding, Korean technical answers, JSON/tool formatting, and regression resistance.

The result is a single checkpoint with no runtime adapter requirement.

Benchmark Growth

The comparison target is the original Gemma4 12B instruction checkpoint.

Benchmark Gemma4 12B original SuperGemma-4-12b-abliterated Delta
Overall public top-5 500 23.8 44.6 +20.8
GPQA Diamond 10.0 19.0 +9.0
MMLU-Pro 17.0 18.0 +1.0
IFEval 61.0 59.0 -2.0
HumanEval+ 18.0 46.0 +28.0
MBPP+ 13.0 81.0 +68.0

Additional internal validation:

Check Result
Public benchmark prompts completed 500 / 500
Blank response ratio 0.0
Hidden-thought leak ratio 0.0
Release-surface response audit findings 0
Release bugcheck 6 / 6
Quickbench full20 overall 95.4
Mega 103 overall 88.7
Original reference Mega 103 overall 84.1

Quantized Variants

Quantized builds are published as separate Hub repos and are linked back to this model through Hub metadata.

Variant Repository Notes
Original BF16 Jiunsong/SuperGemma-4-12b-abliterated This repository
NVF4 / NVFP4 4-bit Jiunsong/SuperGemma-4-12b-abliterated-nvf4 MLX NVFP4 4-bit quantization
MLX 4-bit Jiunsong/SuperGemma-4-12b-abliterated-mlx-4bit MLX affine 4-bit quantization
GGUF 4-bit Jiunsong/SuperGemma-4-12b-abliterated-gguf-4bit llama.cpp GGUF Q4_K_M

Usage

from transformers import AutoModelForMultimodalLM, AutoProcessor

model_id = "Jiunsong/SuperGemma-4-12b-abliterated"
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained(
    model_id,
    dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [{"role": "user", "content": "Write a concise release checklist."}]
inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
    add_generation_prompt=True,
    enable_thinking=False,
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Notes

  • This release is optimized for direct task completion and reduced unnecessary refusals.
  • Benchmarks are measured against the original Gemma4 12B instruction checkpoint using the recorded 500-prompt public top-5 suite.
  • Use the quantized builds when runtime size is more important than exact BF16 fidelity.
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.