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

Libraries

How to use remyxai/SpaceOm with Transformers:

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

pipe = pipeline("image-text-to-text", model="remyxai/SpaceOm")
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("remyxai/SpaceOm")
model = AutoModelForMultimodalLM.from_pretrained("remyxai/SpaceOm", 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 remyxai/SpaceOm with vLLM:

Install from pip and serve model

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

SGLang

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

Update model card with paper, project page, and code links

by nielsr HF Staff - opened Jul 1, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+15

-5

nielsr

Jul 1, 2025

This PR improves the model card for remyxai/SpaceOm by:

Adding an explicit link to the associated research paper (Spatial Mental Modeling from Limited Views) at the top of the card for better discoverability.
Adding a direct link to the official project page (https://mll-lab-nu.github.io/mind-cube).
Adding a direct link to the main GitHub repository (https://github.com/mll-lab-nu/MindCube) for easy access to the source code.

These additions will make it more straightforward for users to find relevant external resources related to the model.

Update model card with paper, project page, and code linkscb26915a

salma-remyx

Remyx AI org Jul 1, 2025

Hi @nielsr , thank you for helping us improve SpaceOm! Before we merge, could you help with two small tweaks?

Benchmark results: The edit removes the existing benchmark table. Could we keep those numbers in place?
Link labeling:
- The project- and code-links you added belong to the paper Spatial Mental Modeling from Limited Views, which uses our model for evaluation.
- To avoid confusion about authorship, let’s label those links under an “External Benchmark” (or similar) heading.
- The official open-source repo for itself is: https://github.com/remyxai/VQASynth (SpatialVLM implementation).

Once those clarifications are in, we’ll be happy to merge.

Update README.md5cfd97d5

Update README.md48344441

nielsr

Jul 6, 2025

Thanks, I've made the changes, feel free to merge and edit.

salma-remyx

Remyx AI org Jul 6, 2025

awesome, thanks again!

salma-remyx changed pull request status to merged Jul 6, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment