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

Libraries

How to use MMR1/MMR1-7B-RL with Transformers:

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

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MMR1/MMR1-7B-RL"
# 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/MMR1-7B-RL",
		"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/MMR1-7B-RL

SGLang

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

Improve model card: Add metadata, paper & code links, and detailed description for MMR1

by nielsr HF Staff - opened Sep 26, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+67

-1

nielsr

Sep 26, 2025

This PR significantly enhances the model card for the MMR1 model, making it more informative and discoverable.

Key changes include:

Adding pipeline_tag: image-text-to-text, library_name: transformers, and license: apache-2.0 to the metadata, which will enable automated features and improve searchability.
Adding the full paper title and a direct link to the Hugging Face paper page.
Adding a clear link to the official GitHub repository.
Providing a detailed overview of the MMR1 model, its contributions, methodology, open resources, and evaluation results, synthesized from the paper abstract and GitHub README.
Adding the BibTeX citation for proper referencing.
Including the full license statement.

No sample usage is added as it was not found in the provided GitHub README, adhering to the guidelines. File information has also been excluded from the model card content as per instructions.

Please review these updates and merge the PR.

Improve model card: Add metadata, paper & code links, and detailed description for MMR1e1a1b47c

Sicong changed pull request status to merged Oct 1, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment