Instructions to use MaxyLee/DeepPerception with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaxyLee/DeepPerception with Transformers:

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

pipe = pipeline("image-text-to-text", model="MaxyLee/DeepPerception")
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("MaxyLee/DeepPerception")
model = AutoModelForImageTextToText.from_pretrained("MaxyLee/DeepPerception")
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 MaxyLee/DeepPerception with vLLM:

Install from pip and serve model

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

SGLang

How to use MaxyLee/DeepPerception 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 "MaxyLee/DeepPerception" \
    --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": "MaxyLee/DeepPerception",
		"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 "MaxyLee/DeepPerception" \
        --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": "MaxyLee/DeepPerception",
		"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 MaxyLee/DeepPerception with Docker Model Runner:
```
docker model run hf.co/MaxyLee/DeepPerception
```

MaxyLee commited on Mar 19, 2025

Commit

150ffbf

verified ·

1 Parent(s): d8f1a52

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -7,4 +7,17 @@ metrics:
 base_model:
 - Qwen/Qwen2-VL-7B-Instruct
 pipeline_tag: image-text-to-text
----

 base_model:
 - Qwen/Qwen2-VL-7B-Instruct
 pipeline_tag: image-text-to-text
+---
+# DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
+Xinyu Ma, Ziyang Ding, Zhicong Luo, Chi Chen, Zonghao Guo, Derek F. Wong, Xiaoyi Feng, Maosong Sun
+-----
+<a href='https://deepperception-kvg.github.io/'><img src='https://img.shields.io/badge/Project-Page-blue'></a>
+<a href='https://arxiv.org/abs/2503.12797'><img src='https://img.shields.io/badge/Paper-PDF-Green'></a>
+<a href='https://github.com/MaxyLee/DeepPerception'><img src='https://img.shields.io/badge/Github-Page-green'></a>
+<a href='https://huggingface.co/datasets/MaxyLee/KVG-Bench'><img src='https://img.shields.io/badge/Benchmark-Huggingface-orange'></a>
+<a href='https://huggingface.co/datasets/MaxyLee/KVG'><img src='https://img.shields.io/badge/Dataset-Huggingface-purple'></a>
+This is the official repository of **DeepPerception**, an MLLM enhanced with cognitive visual perception capabilities.