Instructions to use Kunyang-YU/LookStep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kunyang-YU/LookStep with Transformers:

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

pipe = pipeline("image-text-to-text", model="Kunyang-YU/LookStep")
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("Kunyang-YU/LookStep")
model = AutoModelForMultimodalLM.from_pretrained("Kunyang-YU/LookStep", device_map="auto")
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 Kunyang-YU/LookStep with vLLM:

Install from pip and serve model

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

SGLang

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

nielsr HF Staff commited on 11 days ago

Commit

deade7d

verified ·

1 Parent(s): 23c1f38

Add pipeline tag, library name, and paper/code links

Browse files

This PR improves the model card by:
- Adding the `pipeline_tag` `image-text-to-text` so the model appears in the correct Hub category.
- Adding `library_name: transformers` to enable the corresponding Hub integration.
- Adding links to the paper page and the official LookStep GitHub repository in the content section.

The existing model information, training details, reproduction instructions, and citation are preserved.

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -1,13 +1,16 @@
 ---
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
 ---
 # LookStep
 [简体中文](README_ZH.md)
 ## Model details

 ---
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
 # LookStep
 [简体中文](README_ZH.md)
+This is the official checkpoint for the paper [LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory](https://huggingface.co/papers/2609.02350). The code is available at [https://github.com/kunyang-YU/LookStep](https://github.com/kunyang-YU/LookStep).
 ## Model details