Instructions to use two-tiger/MiMo-VRPRM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use two-tiger/MiMo-VRPRM-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="two-tiger/MiMo-VRPRM-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("two-tiger/MiMo-VRPRM-7B")
model = AutoModelForMultimodalLM.from_pretrained("two-tiger/MiMo-VRPRM-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 two-tiger/MiMo-VRPRM-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "two-tiger/MiMo-VRPRM-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": "two-tiger/MiMo-VRPRM-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/two-tiger/MiMo-VRPRM-7B

SGLang

How to use two-tiger/MiMo-VRPRM-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 "two-tiger/MiMo-VRPRM-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": "two-tiger/MiMo-VRPRM-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 "two-tiger/MiMo-VRPRM-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": "two-tiger/MiMo-VRPRM-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 two-tiger/MiMo-VRPRM-7B with Docker Model Runner:
```
docker model run hf.co/two-tiger/MiMo-VRPRM-7B
```

two-tiger commited on May 31

Commit

f3675d6

verified ·

1 Parent(s): 12687f4

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +10 -14

README.md CHANGED Viewed

@@ -26,13 +26,11 @@ VRPRM is designed to evaluate intermediate reasoning steps for multimodal proble
 ## Training Summary
-The VRPRM paper trains the model with a two-stage recipe:
-1. Supervised fine-tuning cold start on high-quality CoT-PRM data.
 2. Reinforcement learning scaling on lower-cost non-CoT PRM data.
-The release data is derived from VisualPRM400K-style process supervision.
 ## Intended Use
 This model is intended for research on:
@@ -64,19 +62,17 @@ model = AutoModelForVision2Seq.from_pretrained(
 For the complete inference and evaluation pipeline, use the VRPRM project code.
-## Limitations
-- Reward scores depend on the quality of the generated visual reasoning process.
-- Generated reasoning introduces higher latency than direct scalar reward modeling.
-- The model may inherit biases from its base model and process supervision data.
-- Evaluation should be performed on task-specific validation sets before deployment.
 ## Citation
 ```bibtex
-@article{vrprm2026,
-  title={VRPRM: Process Reward Modeling via Visual Reasoning},
-  author={Chen, Xinquan and Yue, Chongying and Liu, Bangwei and Wang, Xuhong and Wang, Yingchun and Lu, Chaochao},
-  year={2026}
 }
 ```

 ## Training Summary
+The [VRPRM](https://arxiv.org/abs/2508.03556) paper trains the model with a two-stage recipe:
+1. Supervised fine-tuning cold start on high-quality CoT-PRM data. Open-sourced on [VRPRM3.6K](https://huggingface.co/datasets/two-tiger/VRPRM3.6K).
 2. Reinforcement learning scaling on lower-cost non-CoT PRM data.
 ## Intended Use
 This model is intended for research on:
 For the complete inference and evaluation pipeline, use the VRPRM project code.
 ## Citation
 ```bibtex
+@misc{chen2026vrprmprocessrewardmodeling,
+      title={VRPRM: Process Reward Modeling via Visual Reasoning},
+      author={Xinquan Chen and Chongying Yue and Bangwei Liu and Xuhong Wang and Yingchun Wang and Chaochao Lu},
+      year={2026},
+      eprint={2508.03556},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2508.03556},
 }
 ```