Instructions to use MMR1/MMR1-Math-v0-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MMR1/MMR1-Math-v0-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="MMR1/MMR1-Math-v0-7B")
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("MMR1/MMR1-Math-v0-7B")
model = AutoModelForMultimodalLM.from_pretrained("MMR1/MMR1-Math-v0-7B")
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 MMR1/MMR1-Math-v0-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MMR1/MMR1-Math-v0-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MMR1/MMR1-Math-v0-7B",
		"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/MMR1/MMR1-Math-v0-7B

SGLang

How to use MMR1/MMR1-Math-v0-7B 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 "MMR1/MMR1-Math-v0-7B" \
    --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": "MMR1/MMR1-Math-v0-7B",
		"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 "MMR1/MMR1-Math-v0-7B" \
        --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": "MMR1/MMR1-Math-v0-7B",
		"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 MMR1/MMR1-Math-v0-7B with Docker Model Runner:
```
docker model run hf.co/MMR1/MMR1-Math-v0-7B
```

nielsr HF Staff commited on Mar 13, 2025

Commit

031c481

verified ·

1 Parent(s): aa8707e

Improve model card: Correct pipeline tag, link to code, and project page

Browse files

This PR improves the model card by:

- Correcting the `pipeline_tag` to `image-text-to-text`.
- Linking to the project page.
- Ensuring the model card has a link to the Github repository.

Files changed (1) hide show

README.md +11 -5

README.md CHANGED Viewed

@@ -1,16 +1,17 @@
 ---
-library_name: transformers
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
-pipeline_tag: visual-question-answering
 tags:
 - multi-modal
 - large-language-model
 ---
 <p align="center">
     <img src="https://github.com/LengSicong/MMR1/blob/main/assets/logo.png?raw=true" width="150" style="margin-bottom: 0.2;"/>
 <p>
@@ -22,6 +23,10 @@ MMR1: Advancing the Frontiers of Multimodal Reasoning</a></h3>
 ## 📰 News
 * **[2025.03.11]**  🔥🔥 Release MMR1-Math-v0, achieving SOTA with only 6k data!
 ## Model Description
 MMR1-Math-v0-7B is a Large Multimodal Model specialized in mathematical tasks. Remarkably, MMR1-Math-v0-7B achieves state-of-the-art performance among open-source 7B multimodal models, competing effectively even against proprietary models with significantly larger parameter sizes—all trained using only 6k carefully curated data instances.
@@ -177,4 +182,5 @@ If you find MMR1 useful for your research and applications, please cite using th
   year={2025},
   howpublished={\url{https://github.com/LengSicong/MMR1}},
 }
 ```

 ---
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+language:
+- en
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
 tags:
 - multi-modal
 - large-language-model
 ---
+```markdown
 <p align="center">
     <img src="https://github.com/LengSicong/MMR1/blob/main/assets/logo.png?raw=true" width="150" style="margin-bottom: 0.2;"/>
 <p>
 ## 📰 News
 * **[2025.03.11]**  🔥🔥 Release MMR1-Math-v0, achieving SOTA with only 6k data!
+## Links
+Project page: https://forjadeforest.github.io/LMM-R1-ProjectPage
+This model was presented in the paper [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://arxiv.org/abs/2503.07536). Code can be found at https://github.com/LengSicong/MMR1
 ## Model Description
 MMR1-Math-v0-7B is a Large Multimodal Model specialized in mathematical tasks. Remarkably, MMR1-Math-v0-7B achieves state-of-the-art performance among open-source 7B multimodal models, competing effectively even against proprietary models with significantly larger parameter sizes—all trained using only 6k carefully curated data instances.
   year={2025},
   howpublished={\url{https://github.com/LengSicong/MMR1}},
 }
+```
 ```