Instructions to use kagakouko/Spatial-Interactor-Qwen3-VL-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kagakouko/Spatial-Interactor-Qwen3-VL-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="kagakouko/Spatial-Interactor-Qwen3-VL-8B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("kagakouko/Spatial-Interactor-Qwen3-VL-8B")
model = AutoModelForMultimodalLM.from_pretrained("kagakouko/Spatial-Interactor-Qwen3-VL-8B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kagakouko/Spatial-Interactor-Qwen3-VL-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kagakouko/Spatial-Interactor-Qwen3-VL-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kagakouko/Spatial-Interactor-Qwen3-VL-8B",
		"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/kagakouko/Spatial-Interactor-Qwen3-VL-8B

SGLang

How to use kagakouko/Spatial-Interactor-Qwen3-VL-8B 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 "kagakouko/Spatial-Interactor-Qwen3-VL-8B" \
    --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": "kagakouko/Spatial-Interactor-Qwen3-VL-8B",
		"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 "kagakouko/Spatial-Interactor-Qwen3-VL-8B" \
        --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": "kagakouko/Spatial-Interactor-Qwen3-VL-8B",
		"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 kagakouko/Spatial-Interactor-Qwen3-VL-8B with Docker Model Runner:
```
docker model run hf.co/kagakouko/Spatial-Interactor-Qwen3-VL-8B
```

kagakouko commited on 24 days ago

Commit

e732ce5

verified ·

1 Parent(s): b4fa224

Simplify model cards and add direct loading examples

Browse files

Files changed (1) hide show

README.md +13 -28

README.md CHANGED Viewed

@@ -52,39 +52,24 @@ trajectories.
   <img src="https://raw.githubusercontent.com/ZJU-OmniAI/Spatial-Interactor/main/assets/readme/presentation-preview.webp?v=20260916" width="100%" alt="Spatial-Interactor 20-page presentation">
 </p>
-## How Spatial-Interactor learns
-<p align="center">
-  <img src="https://raw.githubusercontent.com/ZJU-OmniAI/Spatial-Interactor/main/assets/readme/opd.webp" width="100%" alt="On-Policy Distillation pipeline">
-</p>
-L1 and L2 establish local state-transition modeling. On L3, verifiable answer
-rewards supervise the result while same-prefix privileged distillation guides
-the intermediate reasoning process.
-## Usage
-All four checkpoints are listed in the
-[Spatial-Interactor collection](https://huggingface.co/collections/kagakouko/spatial-interactor).
-Use the standard Transformers interface for the base model and load this
-repository in place of the base identifier:
 ```python
 model_id = "kagakouko/Spatial-Interactor-Qwen3-VL-8B"
 ```
-For video evaluation, preserve chronological frame order and use the frame
-budget specified by the target benchmark. The paper's main video evaluation
-uses 32 ordered frames.
-## Training summary
-The SFT stage uses the reported L1-L2 split of LSI-108K together with the public
-spatial QA mixture described in the paper. OPD starts from that SFT checkpoint
-and combines verifiable answer rewards with CoT-only privileged
-self-distillation on long-horizon video questions. The visual encoder remains
-frozen while the language model and multimodal projector are updated.
 ## Citation

   <img src="https://raw.githubusercontent.com/ZJU-OmniAI/Spatial-Interactor/main/assets/readme/presentation-preview.webp?v=20260916" width="100%" alt="Spatial-Interactor 20-page presentation">
 </p>
+## Load
 ```python
+import torch
+from transformers import AutoModelForImageTextToText, AutoProcessor
 model_id = "kagakouko/Spatial-Interactor-Qwen3-VL-8B"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForImageTextToText.from_pretrained(
+    model_id, torch_dtype=torch.bfloat16, device_map="auto",
+)
 ```
+Use the base model's [image/video input format](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct).
+No privileged trace or additional teacher is needed for inference.
+Weights, tokenizer, processor, and chat template are included.
+See the [training guide](https://github.com/ZJU-OmniAI/Spatial-Interactor/blob/main/docs/TRAINING.md)
+for SFT and OPD.
 ## Citation