Instructions to use xianyao/persim-gemma-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xianyao/persim-gemma-12b with Transformers:

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

pipe = pipeline("text-generation", model="xianyao/persim-gemma-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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("xianyao/persim-gemma-12b")
model = AutoModelForMultimodalLM.from_pretrained("xianyao/persim-gemma-12b", 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 xianyao/persim-gemma-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xianyao/persim-gemma-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": "xianyao/persim-gemma-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xianyao/persim-gemma-12b

SGLang

How to use xianyao/persim-gemma-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 "xianyao/persim-gemma-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": "xianyao/persim-gemma-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "xianyao/persim-gemma-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": "xianyao/persim-gemma-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xianyao/persim-gemma-12b with Docker Model Runner:
```
docker model run hf.co/xianyao/persim-gemma-12b
```

persim-gemma-12b

An open-weight Big-Five personality → household layout generator for the PerSim pipeline (arXiv:2607.00022, IROS 2026). Given the pipeline's generate_layouts.py prompt (scene + persona + item vocabulary), it produces personality-conditioned placements as strict JSON:

{
  "room_movable_items": {"kitchen_0": ["mug_0", "plate_0", ...], ...},
  "initial_object_positions": {"mug_0": {"relation": "on", "anchor_object": "countertop_tpuwys_0"}, ...}
}

The pipeline works with any OpenAI-compatible endpoint; this model is a ready-made open option for the layout stage (the paper's fine-tuned Gemini 2.5 Flash cannot be redistributed). Outputs inherit only the pipeline's automatic checks — no plausibility or paper-equivalence claims.

Training

QLoRA (r=16) on google/gemma-4-12B-it, 2 epochs on one RTX 4090. Data: persim-sft human placement anchors (rigidity dropped) + layout demonstrations self-generated by the base model on the real pipeline prompts and filtered through check_layouts.py. No proprietary-model outputs in the supervision.

Usage

vllm serve xianyao/persim-gemma-12b \
  --max-model-len 16384 \
  --override-generation-config '{"repetition_penalty": 1.05}'

python generate_persona.py      --model google/gemma-4-12B-it      # base model
python generate_layouts.py      --model xianyao/persim-gemma-12b   # this model
python generate_trajectories.py --model google/gemma-4-12B-it      # base model

Also answers the standalone anchor query (Personality: O=..., C=...\nObject: mug → {"rooms": [...], "cooccurrence": [...]}).

Limitations

The largest shipped scene (house_single_floor, 120–240 items) is unreliable: generation can run away into numbered duplicates until the token limit. repetition_penalty=1.05 plus the pipeline's retries partially compensate. Smaller scenes are stable.
Trained on the pipeline's five scenes and item vocabulary; new scenes are untested.
Layout plausibility is not validated — format and containment checks only.

Citation

@article{li2026personalize,
  title   = {When to Personalize Household Object Search: A Rigidity-Gated Hybrid Policy},
  author  = {Li, Xianyao and Wang, Yuhai and Xiao, Hu and Smith, Kaleb and Ye, Gilbert Yang and Du, Eric Jing},
  journal = {arXiv preprint arXiv:2607.00022},
  year    = {2026}
}

Derived from Gemma. Gemma is provided by Google; use is subject to the base model's license and terms.

Downloads last month: 1,323

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for xianyao/persim-gemma-12b

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Adapter

(36)

this model

Dataset used to train xianyao/persim-gemma-12b

Paper for xianyao/persim-gemma-12b

When to Personalize Household Object Search: A Rigidity-Gated Hybrid Policy

Paper • 2607.00022 • Published about 1 month ago