Instructions to use OraRL/Video-ORA-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OraRL/Video-ORA-9B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OraRL/Video-ORA-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("OraRL/Video-ORA-9B")
model = AutoModelForMultimodalLM.from_pretrained("OraRL/Video-ORA-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 OraRL/Video-ORA-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OraRL/Video-ORA-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": "OraRL/Video-ORA-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/OraRL/Video-ORA-9B

SGLang

How to use OraRL/Video-ORA-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 "OraRL/Video-ORA-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": "OraRL/Video-ORA-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 "OraRL/Video-ORA-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": "OraRL/Video-ORA-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 OraRL/Video-ORA-9B with Docker Model Runner:
```
docker model run hf.co/OraRL/Video-ORA-9B
```

lyhisme commited on 1 day ago

Commit

00798e7

verified ·

1 Parent(s): d4e24ae

Refresh Video-ORA-9B model card

Browse files

Files changed (1) hide show

README.md +18 -20

README.md CHANGED Viewed

@@ -20,26 +20,24 @@ tags:
 # Video-ORA-9B
-[Paper](https://arxiv.org/abs/2608.20492) ·
-[Project page](https://orarl.github.io/) ·
-[Code](https://github.com/HVision-NKU/OraRL) ·
-[Evaluation data](https://huggingface.co/datasets/OraRL/OraRL-Eval)
-Video-ORA-9B is the 9B model released with **Annotations as Rollouts:
-Efficient and Scalable Reinforcement Learning for Video MLLMs**. It is
-fine-tuned from [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) with
-OraRL across seven video and multimodal task families:
-- temporal grounding
-- visual tracking
-- image and video segmentation
-- spatial grounding
-- spatial-temporal grounding
-- video question answering
-- spatial intelligence
-The model is evaluated with direct, task-native answers rather than generated
-chain-of-thought.
 ## Model summary

 # Video-ORA-9B
+[[🏠 Homepage](https://orarl.github.io/)] [[📖 Arxiv Paper](https://arxiv.org/abs/2608.20492)] [[🤗 Evaluation Data](https://huggingface.co/datasets/OraRL/OraRL-Data/tree/main/OraRL-eval-data)] [[💻 Code](https://github.com/HVision-NKU/OraRL)]
+We release **Video-ORA-9B**, the 9B model trained with **OraRL (Annotations as
+Rollouts)** for **unified video understanding**.
+Starting from [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B), OraRL
+post-training equips one model to handle seven task families with direct,
+task-native answers and no chain-of-thought decoding.
+## Supported task families
+- Temporal grounding
+- Visual tracking
+- Image and video segmentation
+- Spatial grounding
+- Spatial-temporal grounding
+- Video question answering
+- Spatial intelligence
 ## Model summary