Instructions to use array/Qwen2.5-VL-MullGRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use array/Qwen2.5-VL-MullGRPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="array/Qwen2.5-VL-MullGRPO", trust_remote_code=True)
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("array/Qwen2.5-VL-MullGRPO", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("array/Qwen2.5-VL-MullGRPO", trust_remote_code=True)
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 array/Qwen2.5-VL-MullGRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "array/Qwen2.5-VL-MullGRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "array/Qwen2.5-VL-MullGRPO",
		"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/array/Qwen2.5-VL-MullGRPO

SGLang

How to use array/Qwen2.5-VL-MullGRPO 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 "array/Qwen2.5-VL-MullGRPO" \
    --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": "array/Qwen2.5-VL-MullGRPO",
		"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 "array/Qwen2.5-VL-MullGRPO" \
        --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": "array/Qwen2.5-VL-MullGRPO",
		"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 array/Qwen2.5-VL-MullGRPO with Docker Model Runner:
```
docker model run hf.co/array/Qwen2.5-VL-MullGRPO
```

Repository: [https://github.com/arijitray1993/mull-tokens]
Paper: [https://arxiv.org/abs/2512.10941]

How to Get Started with the Model

WORK IN PROGRESS: more details to be added soon!

It is highly recommended to install this version of transformers: https://github.com/arijitray1993/Mirage

git clone https://github.com/arijitray1993/Mirage
pip install -e ./transformers/.

Next, clone this repo: https://github.com/arijitray1993/mull-tokens.

We use a custom Qwen2.5 VL model. There is no change to the architecture, just some new tokens added.

% pip install qwen-vl-utils[decord]==0.0.8

import importlib
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor

Qwen2_5_VLForConditionalGeneration = importlib.import_module(
            'models.mmlatentdiscrete_qwen_vl'
        ).Qwen2_5_VLForConditionalGeneration

model = Qwen2_5_VLForConditionalGeneration.from_pretrained("array/Qwen2.5-VL-MullGRPO")
processor = AutoProcessor.from_pretrained(
    "array/Qwen2.5-VL-MullGRPO",
    trust_remote_code=True
)

Citation [optional]

@misc{ray2025mulltokensmodalityagnosticlatentthinking,
      title={Mull-Tokens: Modality-Agnostic Latent Thinking}, 
      author={Arijit Ray and Ahmed Abdelkader and Chengzhi Mao and Bryan A. Plummer and Kate Saenko and Ranjay Krishna and Leonidas Guibas and Wen-Sheng Chu},
      year={2025},
      eprint={2512.10941},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.10941}, 
}