Instructions to use UnderTides/Embodied-Navigator-7B-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UnderTides/Embodied-Navigator-7B-GRPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="UnderTides/Embodied-Navigator-7B-GRPO")
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("UnderTides/Embodied-Navigator-7B-GRPO")
model = AutoModelForMultimodalLM.from_pretrained("UnderTides/Embodied-Navigator-7B-GRPO", 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 UnderTides/Embodied-Navigator-7B-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UnderTides/Embodied-Navigator-7B-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UnderTides/Embodied-Navigator-7B-GRPO",
		"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/UnderTides/Embodied-Navigator-7B-GRPO

SGLang

How to use UnderTides/Embodied-Navigator-7B-GRPO 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 "UnderTides/Embodied-Navigator-7B-GRPO" \
    --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": "UnderTides/Embodied-Navigator-7B-GRPO",
		"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 "UnderTides/Embodied-Navigator-7B-GRPO" \
        --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": "UnderTides/Embodied-Navigator-7B-GRPO",
		"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 UnderTides/Embodied-Navigator-7B-GRPO with Docker Model Runner:
```
docker model run hf.co/UnderTides/Embodied-Navigator-7B-GRPO
```

Update pipeline tag and paper link

by nielsr HF Staff - opened 4 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-5

Files changed (1) hide show

README.md +4 -5

README.md CHANGED Viewed

@@ -1,9 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
-library_name: transformers
-pipeline_tag: image-text-to-text
 language:
 - en
 tags:
 - vision-language
 - vision-language-navigation
@@ -20,7 +20,7 @@ tags:
 [Project Page](https://zju-omniai.github.io/Embodied-Navigator/) |
 [Code](https://github.com/ZJU-OmniAI/Embodied-Navigator) |
-[Paper](https://arxiv.org/)
 Embodied-Navigator-7B-GRPO is the released navigation policy checkpoint for
 Embodied-Navigator. It adapts Qwen2.5-VL-7B to continuous vision-language
@@ -206,5 +206,4 @@ authors. Refer to the project repository for future license updates.
 Hongyan Feng, Sunlai Chen, Xuanyu Liu, Miao Pan, Yangfan Xie, Yuxiang Cui,
 Zhongxiang Zhou, Rong Xiong, Wenqi Zhang, Jianwei Yin, Yueting Zhuang, and
-Xuhong Zhang.

 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 language:
 - en
+library_name: transformers
+pipeline_tag: robotics
 tags:
 - vision-language
 - vision-language-navigation
 [Project Page](https://zju-omniai.github.io/Embodied-Navigator/) |
 [Code](https://github.com/ZJU-OmniAI/Embodied-Navigator) |
+[Paper](https://huggingface.co/papers/2608.17512)
 Embodied-Navigator-7B-GRPO is the released navigation policy checkpoint for
 Embodied-Navigator. It adapts Qwen2.5-VL-7B to continuous vision-language
 Hongyan Feng, Sunlai Chen, Xuanyu Liu, Miao Pan, Yangfan Xie, Yuxiang Cui,
 Zhongxiang Zhou, Rong Xiong, Wenqi Zhang, Jianwei Yin, Yueting Zhuang, and
+Xuhong Zhang.