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 | |
| from pathlib import Path | |
| import tomllib | |
| RELEASE_ROOT = Path(__file__).resolve().parents[1] | |
| def test_install_metadata_and_console_scripts() -> None: | |
| with (RELEASE_ROOT / "pyproject.toml").open("rb") as handle: | |
| metadata = tomllib.load(handle) | |
| project = metadata["project"] | |
| assert project["name"] == "orarl" | |
| assert project["requires-python"] == ">=3.10" | |
| # The trainer ships inside this distribution, so no external runtime pin. | |
| assert not any(dependency.startswith("verl") for dependency in project["dependencies"]) | |
| assert project["license"] == "Apache-2.0" | |
| assert project["license-files"] == ["LICENSE", "NOTICE"] | |
| assert project["optional-dependencies"]["hf"] == ["huggingface_hub"] | |
| assert project["scripts"] == { | |
| "orarl-train": "orarl.cli.train:main", | |
| "orarl-eval": "orarl.cli.evaluate:main", | |
| "orarl-eval-data": "orarl.cli.eval_data:main", | |
| "orarl-prepare": "orarl.cli.prepare:main", | |
| } | |
| data_files = metadata["tool"]["setuptools"]["data-files"] | |
| assert data_files["share/orarl"] == ["environment.yml", "requirements-cu129.txt"] | |
| assert data_files["share/orarl/configs"] == ["configs/*.yaml"] | |
| assert data_files["share/orarl/docs"] == ["docs/*.md"] | |
| assert data_files["share/orarl/scripts"] == ["scripts/*.py", "scripts/*.sh"] | |
| def test_install_ships_every_evaluator() -> None: | |
| with (RELEASE_ROOT / "pyproject.toml").open("rb") as handle: | |
| metadata = tomllib.load(handle) | |
| installed: set[Path] = set() | |
| for target, patterns in metadata["tool"]["setuptools"]["data-files"].items(): | |
| if not target.startswith("share/orarl/eval"): | |
| continue | |
| for pattern in patterns: | |
| installed.update(RELEASE_ROOT.glob(pattern)) | |
| # Importing an evaluator during the suite drops bytecode next to the source. | |
| shipped = { | |
| path | |
| for path in (RELEASE_ROOT / "eval").rglob("*") | |
| if path.is_file() and "__pycache__" not in path.parts | |
| } | |
| assert shipped | |
| assert sorted(shipped - installed) == [] | |
| def test_apache_attribution_files_are_present() -> None: | |
| license_text = (RELEASE_ROOT / "LICENSE").read_text(encoding="utf-8") | |
| notice_text = (RELEASE_ROOT / "NOTICE").read_text(encoding="utf-8") | |
| assert "Apache License" in license_text | |
| assert "Version 2.0" in license_text | |
| assert "ByteDance Ltd." in notice_text | |