Instructions to use Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic")
model = AutoModelForMultimodalLM.from_pretrained("Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic

SGLang

How to use Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic with Docker Model Runner:
```
docker model run hf.co/Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

gemma-4-26B-A4B-it QAT (unquantized) — uncensored heretic

Uncensored (abliterated) variant of google/gemma-4-26B-A4B-it-qat-q4_0-unquantized, the QAT-trained bf16 checkpoint intended as the precursor for q4_0 / W4A4 / W4A16 quantization.

Produced with Heretic (directional ablation + Optuna kernel optimization). This is the full merged unquantized bf16 model — quantize from this to your favorite 4-bit format; the abliteration deltas are already baked into the weights, so downstream calibration works exactly as on any QAT checkpoint.

Method & provenance

Abliteration kernel (direction index + per-component weight kernels over 30 layers) was optimized on the stock google/gemma-4-26B-A4B-it base: 200-trial Optuna study, Pareto-optimal trial selected to minimize KL divergence at maximum refusal suppression.
The kernel was then transferred to the QAT-unquantized base, with residual directions recomputed on that base (mean per-layer direction cosine vs stock: 0.973, ~0.976 in the ablated layer band — same refusal circuit, so the transfer is faithful).
Ablation applied to attention out-projections (LoRA-merged), dense MLP down-projections (LoRA-merged), and all 128 fused MoE expert down-projections per layer (ablation baked into the 3D fused weights — see reproduce/reproduce.json for exact parameters).

Evaluation

Metric	QAT base (no ablation)	This model
Refusal-keyword rate, worst-case "harmful" set (lower = less refusing)	100/100	24/100
KL divergence from base (harmless prompts, lower = less damage)	0	0.078
ARC-Challenge (chat MCQ)	93.86%	94.11%
Adult/romance creative-writing compliance (10-prompt suite)	9/10	10/10

Reference points on the stock (non-QAT) base with the same kernel: ARC-C 96.67% (stock unmodified: 96.76%), HellaSwag chat-MCQ 87.0% (stock: 87.9%), IFEval prompt-strict 88.5% / loose 90.8%, KL 0.090, refusal keywords 18/100. The ~3 pt ARC gap between QAT and stock bases is attributable to QAT training itself, not the abliteration (93.86 → 94.11 across ablation on the QAT base).

KL divergence 0.078 is well below the ~0.5 level generally associated with noticeable capability damage.

Intended use

A local creative-writing and analysis assistant for adult romance / adult-entertainment authorship, and general-purpose LAN workhorse duty. The residual keyword rate above is dominated by worst-case malicious-instruction prompts, not adult content, where compliance is effectively complete.

Released under Apache 2.0 (inherited from the base model). Provided as-is, no warranty; you are responsible for how you use it.

Reproducing

See reproduce/ for the exact Heretic parameters (JSON), dependency snapshot, and SHA256SUMS of the weight shards. The abliteration was run with a patched Heretic (Gemma-4 fused-expert support + low-RAM sequential loading); parameter semantics are unchanged.

Downloads last month: 14

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for Mitchins/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Finetuned

(162)

this model

Quantizations

1 model