Image-Text-to-Text
Transformers
Safetensors
qwen3_5
vllm
video
multimodal
reinforcement-learning
temporal-grounding
object-tracking
video-segmentation
visual-question-answering
spatial-reasoning
qwen3.5
conversational
Instructions to use OraRL/Video-ORA-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
| from __future__ import annotations | |
| import sys | |
| import tempfile | |
| import unittest | |
| from pathlib import Path | |
| ORARL_ROOT = Path(__file__).resolve().parents[1] | |
| if str(ORARL_ROOT) not in sys.path: | |
| sys.path.insert(0, str(ORARL_ROOT)) | |
| from orarl.data import ( # noqa: E402 | |
| SchemaError, | |
| canonicalize_record, | |
| prompt_identity, | |
| validate_record, | |
| ) | |
| class DataSchemaTests(unittest.TestCase): | |
| def test_canonicalizes_aliases_and_relative_media(self) -> None: | |
| with tempfile.TemporaryDirectory() as raw_tmp: | |
| tmp_path = Path(raw_tmp) | |
| media_root = tmp_path / "media" | |
| image = media_root / "frames" / "one.jpg" | |
| image.parent.mkdir(parents=True) | |
| image.write_bytes(b"image") | |
| record = canonicalize_record( | |
| { | |
| "question": " Which object is red? ", | |
| "ground_truth": {"label": "ball"}, | |
| "image": "frames/one.jpg", | |
| "metadata": {"split": "train"}, | |
| }, | |
| problem_type="spatial grounding", | |
| source="unit_source", | |
| family="spatial", | |
| media_root=media_root, | |
| require_media=True, | |
| ) | |
| self.assertEqual(record["problem"], " Which object is red? ") | |
| self.assertEqual(record["answer"], {"label": "ball"}) | |
| self.assertEqual(record["images"], [str(image)]) | |
| self.assertEqual(record["videos"], []) | |
| self.assertEqual(record["problem_type"], "spatial grounding") | |
| self.assertEqual(record["source"], "unit_source") | |
| self.assertEqual(record["metadata"], {"split": "train"}) | |
| def test_rejects_empty_oracle_labels(self) -> None: | |
| answers = [None, "", " ", [], {}, {"label": ""}, float("nan")] | |
| for answer in answers: | |
| with self.subTest(answer=answer): | |
| record = { | |
| "problem": "Question", | |
| "answer": answer, | |
| "images": ["image.jpg"], | |
| "videos": [], | |
| "problem_type": "spatial grounding", | |
| "source": "unit_source", | |
| } | |
| with self.assertRaisesRegex(SchemaError, "oracle label"): | |
| validate_record(record) | |
| def test_media_existence_is_switchable(self) -> None: | |
| with tempfile.TemporaryDirectory() as raw_tmp: | |
| record = { | |
| "problem": "Question", | |
| "answer": "Answer", | |
| "images": [str(Path(raw_tmp) / "missing.jpg")], | |
| "videos": [], | |
| "problem_type": "spatial grounding", | |
| "source": "unit_source", | |
| } | |
| validate_record(record, require_media=False) | |
| with self.assertRaisesRegex(SchemaError, "does not exist"): | |
| validate_record(record, require_media=True) | |
| def test_prompt_identity_normalizes_text_and_paths(self) -> None: | |
| with tempfile.TemporaryDirectory() as raw_tmp: | |
| tmp_path = Path(raw_tmp) | |
| first = { | |
| "problem": "<image> Which OBJECT is red?", | |
| "answer": "ball", | |
| "images": [str(tmp_path / "frames" / ".." / "one.jpg")], | |
| "videos": [], | |
| "problem_type": "Spatial Grounding", | |
| "source": "one", | |
| } | |
| second = { | |
| **first, | |
| "problem": "which object is red?", | |
| "images": [str(tmp_path / "one.jpg")], | |
| "source": "two", | |
| } | |
| self.assertEqual(prompt_identity(first), prompt_identity(second)) | |
| def test_rejects_remote_media_reference(self) -> None: | |
| with self.assertRaisesRegex(SchemaError, "remote media"): | |
| canonicalize_record( | |
| { | |
| "problem": "Question", | |
| "answer": "Answer", | |
| "video": "https://example.invalid/clip.mp4", | |
| }, | |
| problem_type="video_qa_mc", | |
| source="unit_source", | |
| ) | |
| if __name__ == "__main__": | |
| unittest.main() | |