Instructions to use mxlin043/EmbRACE-Qwen3.5-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mxlin043/EmbRACE-Qwen3.5-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="mxlin043/EmbRACE-Qwen3.5-9B")
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("mxlin043/EmbRACE-Qwen3.5-9B")
model = AutoModelForMultimodalLM.from_pretrained("mxlin043/EmbRACE-Qwen3.5-9B", 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 mxlin043/EmbRACE-Qwen3.5-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mxlin043/EmbRACE-Qwen3.5-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mxlin043/EmbRACE-Qwen3.5-9B",
		"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/mxlin043/EmbRACE-Qwen3.5-9B

SGLang

How to use mxlin043/EmbRACE-Qwen3.5-9B 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 "mxlin043/EmbRACE-Qwen3.5-9B" \
    --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": "mxlin043/EmbRACE-Qwen3.5-9B",
		"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 "mxlin043/EmbRACE-Qwen3.5-9B" \
        --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": "mxlin043/EmbRACE-Qwen3.5-9B",
		"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 mxlin043/EmbRACE-Qwen3.5-9B with Docker Model Runner:
```
docker model run hf.co/mxlin043/EmbRACE-Qwen3.5-9B
```

EmbRACE-Qwen3.5-9B

Dataset · Viewer · Paper · Code

Qwen3.5-9B fine-tuned on the dataset part of EmbRACE. The model acts as an embodied agent in the closed loop. At every step it receives the instruction and its egocentric frames and answers with a rationale and the next action.

Interface

The model is run with the protocol of the EmbRACE evaluation code, which builds the prompts. Each task is one multi-turn conversation whose system prompt holds the instruction and the action space. The conversation keeps the initial frame and the 13 most recent frames, the last of which is the current one, so a request carries at most 14 images. Every earlier frame is followed by the model's reply to it. The model answers

<reasoning>...</reasoning><action>ACTION</action>

where ACTION is one of MoveForward, MoveBackward, TurnLeft, TurnRight, LookUp, LookDown, OpenDoor, Pick, Drop, MidwayTarget and Finish.

Usage

Serve the model with vLLM.

CUDA_VISIBLE_DEVICES=0 vllm serve mxlin043/EmbRACE-Qwen3.5-9B \
    --served-model-name embrace-qwen35-9b \
    --host 127.0.0.1 --port 8000 \
    --dtype bfloat16 \
    --max-model-len 32768 \
    --limit-mm-per-prompt '{"image": 16}'

Send the following fields with every request, as the evaluation code does. The checkpoint does not set them as defaults.

Field	Value
`temperature`	0.7
`top_p`	0.8
`top_k`	20
`min_p`	0.0
`presence_penalty`	1.5
`chat_template_kwargs`	`{"enable_thinking": false}`

To run the benchmark with the evaluation code, add an entry to configs/vlm_models.yaml

  - match: embrace-qwen35-9b
    provider: local_vllm
    sampling: qwen_instruct
    extra_body:
      chat_template_kwargs: {enable_thinking: false}

and start the evaluation with the simulator on another GPU. The README of the code describes how to install the simulator and download the benchmark.

License

The weights are released under the Creative Commons Attribution-NonCommercial 4.0 license, the license of the EmbRACE data, for research use with attribution. The base model Qwen3.5-9B is released by the Qwen team under the Apache 2.0 license, a copy of which is included as LICENSE-Qwen3.5-9B.

Citation

@article{lin2025embrace,
  title={EmbRACE: Embodied Reasoning and Action in Complex Environments},
  author={Lin, Mingxian and Huang, Wei and Li, Yitang and Jiang, Chengjie and Wu, Kui and Zhong, Fangwei and Chen, Weikai and Qian, Shengju and Wang, Xin and Qi, Xiaojuan},
  journal={arXiv preprint arXiv:2507.10548},
  year={2025}
}

Downloads last month: -

Safetensors

Model size

1.47M params

Tensor type

BF16

Model tree for mxlin043/EmbRACE-Qwen3.5-9B

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(939)

this model

Dataset used to train mxlin043/EmbRACE-Qwen3.5-9B

Paper for mxlin043/EmbRACE-Qwen3.5-9B

EmbRACE-3K: Embodied Reasoning and Action in Complex Environments

Paper • 2507.10548 • Published Jul 14, 2025 • 37