Instructions to use qiuxi337/gemma-3-12b-it-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qiuxi337/gemma-3-12b-it-grpo with Transformers:

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

pipe = pipeline("image-text-to-text", model="qiuxi337/gemma-3-12b-it-grpo")
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("qiuxi337/gemma-3-12b-it-grpo")
model = AutoModelForMultimodalLM.from_pretrained("qiuxi337/gemma-3-12b-it-grpo")
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 qiuxi337/gemma-3-12b-it-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qiuxi337/gemma-3-12b-it-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qiuxi337/gemma-3-12b-it-grpo",
		"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/qiuxi337/gemma-3-12b-it-grpo

SGLang

How to use qiuxi337/gemma-3-12b-it-grpo 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 "qiuxi337/gemma-3-12b-it-grpo" \
    --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": "qiuxi337/gemma-3-12b-it-grpo",
		"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 "qiuxi337/gemma-3-12b-it-grpo" \
        --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": "qiuxi337/gemma-3-12b-it-grpo",
		"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 qiuxi337/gemma-3-12b-it-grpo with Docker Model Runner:
```
docker model run hf.co/qiuxi337/gemma-3-12b-it-grpo
```

Gemma-3-12B-GRPO trained with GRPO via LoRA

Due to limited available computational resources, we randomly sampled 500 data points from MedQA-USMLE using a methodology and conducted preliminary GRPO experiments with LoRA using the Unsloth framework. We are now releasing this as a preview version. More experiments and explorations are currently underway, and a technical report is in preparation. Thank you for your patience. We conduct the experiments on one RTX-A6000 Ada (48GB VRAM).

Evaluation Results

The model is evaluated on four benchmark datasets: MMLU, MMLU-Pro, CMMU, GSM8K, GPQA. The experimental results are summarized in Table 1, with comprehensive analyses provided in the Detailed Results section.

Tab.1 Evaluation results.

Dataset	Gemma-3-12b-it	Gemma3-12b-GRPO
MMLU	65.51	70.13
MMLU-Pro	60.17	59.99
CMMLU	54.81	57.07
GSM8K	91.58	91.81
GPQA	34.98	34.23

Requirements

pip install torch==2.6.0 torchaudio==2.6.0 torchvision==0.21.0 -i --index-url https://download.pytorch.org/whl/cu124
pip install transformer vllm bitsandbytes peft
pip install flash-attn --no-build-isolation

Run with vLLM

You can use the following script to run with vLLM.

vllm serve qiuxi337/gemma-3-12b-it-grpo \
     --gpu-memory-utilization 0.85 \
     --max-model-len 4096 \
     --served-model-name gemma3-12b-grpo \
     --api-key your_api_key

Detail Results

MMLU

Fig.1 The results on the MMLU benchmark.

Fig.2 The results on the MMLU-Humanities

Fig.3 The results on the MMLU-Social Science

Fig.4 The results on the MMLU-STEM

Fig.5 The results on the MMLU-Other

MMLU-Pro

Fig.6 The results on the MMLU-Pro

CMMLU

Fig.7 The results on the CMMLU benchmark.

Fig.8 The results on the CMMLU-Humanities

Fig.9 The results on the CMMLU-Social Science

Fig.10 The results on the CMMLU-STEM

Fig.11 The results on the CMMLU-Other

Fig.12 The results on the CMMLU-China Specific

Acknowledge

Gemma-3-12b-it

Unlsoth

Citation

@software{Qiu_Open-Medical-R1,
author = {Qiu, Zhongxi and Zhang, Zhang and Hu, Yan and Li, Heng and Liu, Jiang},
license = {MIT},
title = {{Open-Medical-R1}},
url = {https://github.com/Qsingle/open-medical-r1},
version = {0.1}
}

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

F16

Model tree for qiuxi337/gemma-3-12b-it-grpo

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Finetuned

(357)

this model

Merges

1 model

qiuxi337
/

gemma-3-12b-it-grpo