Instructions to use grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B with Transformers:

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

pipe = pipeline("image-text-to-text", model="grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B")
model = AutoModelForImageTextToText.from_pretrained("grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B")
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

vLLM

How to use grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B",
		"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/grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B

SGLang

How to use grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B 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 "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B" \
    --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": "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B",
		"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 "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B" \
        --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": "grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B",
		"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 grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B with Docker Model Runner:
```
docker model run hf.co/grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B

ORBA (Orthogonal Rotational Bounded Ablation) has been applied to several layers in this model, to both mlp.down_proj.weight and self_attn.o_proj.weight streams, along with a few supporting techniques. Preserving norms at the neuron level also ensured numerical conservation of the Frobenius norm for each stream subjected to intervention.

Some refusal behaviors have been geometrically ablated, refusal being a classic high-contrast case that has been well-studied. Safety knowledge and awareness appears to be intact. We posit that a refusal persona was ablated. The vision stack remains part of the model was not subjected to intervention. There are rare token-level glitches in the output; it's possible that quantization errors arising from measurement against a 4-bit bitsandbytes model contibuted to this, though it's also possible that GeLU is less forgiving of errors as an activation function.

More exact details of the intervention will be forthcoming.

Downloads last month: 3

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for grimjim/gemma-3-12b-it-orthogonal-rotation-bounded-ablation-v1-12B

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Finetuned

(355)

this model

Quantizations

3 models