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-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OraRL/Video-ORA-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="OraRL/Video-ORA-4B") 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-4B") model = AutoModelForMultimodalLM.from_pretrained("OraRL/Video-ORA-4B", 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-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OraRL/Video-ORA-4B" # 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-4B", "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-4B
- SGLang
How to use OraRL/Video-ORA-4B 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-4B" \ --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-4B", "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-4B" \ --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-4B", "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-4B with Docker Model Runner:
docker model run hf.co/OraRL/Video-ORA-4B
| from __future__ import annotations | |
| import subprocess | |
| import sys | |
| from pathlib import Path | |
| import pytest | |
| RELEASE_ROOT = Path(__file__).resolve().parents[1] | |
| sys.path.insert(0, str(RELEASE_ROOT)) | |
| from orarl.cli import evaluate # noqa: E402 | |
| EVAL_TASK_ROOT = RELEASE_ROOT / "eval" / "task" | |
| # One entry point per paper task family, so a release cannot drop a family. | |
| FAMILY_ENTRY_POINTS = { | |
| "video_qa": "eval_vllm.py", | |
| "spatial_intelligence": "revsi/eval_revsi_vllm.py", | |
| "temporal_grounding": "temporal_grounding/eval_timelens_hf.py", | |
| "spatial_grounding": "spatial_grounding/eval_refcoco_vllm.py", | |
| "tracking": "tracking/eval_tracking_vllm.py", | |
| "spatial_temporal_grounding": "spatial_temporal_grounding/eval_stvg_vllm.py", | |
| "segmentation": "segmentation/eval_seg_vllm.py", | |
| } | |
| def test_every_task_family_ships_an_entry_point() -> None: | |
| missing = sorted( | |
| family | |
| for family, relative in FAMILY_ENTRY_POINTS.items() | |
| if not (EVAL_TASK_ROOT / relative).is_file() | |
| ) | |
| assert missing == [] | |
| assert (EVAL_TASK_ROOT / "eval.sh").is_file() | |
| assert (EVAL_TASK_ROOT / "mmsi" / "eval_mmsi_transformers.py").is_file() | |
| assert (EVAL_TASK_ROOT / "mindcube" / "data_utils.py").is_file() | |
| def test_evaluator_is_discovered_without_external_runtime( | |
| monkeypatch: pytest.MonkeyPatch, | |
| tmp_path: Path, | |
| ) -> None: | |
| monkeypatch.delenv("ORARL_EVALUATOR", raising=False) | |
| monkeypatch.delenv("ORARL_RUNTIME_ROOT", raising=False) | |
| monkeypatch.setattr(evaluate, "find_spec", lambda _: None) | |
| monkeypatch.chdir(tmp_path) | |
| assert evaluate._discover_evaluator(None) == (EVAL_TASK_ROOT / "eval.sh").resolve() | |
| def test_shipped_shell_evaluators_parse(relative: str) -> None: | |
| result = subprocess.run( | |
| ["bash", "-n", str(EVAL_TASK_ROOT / relative)], | |
| capture_output=True, | |
| text=True, | |
| check=False, | |
| ) | |
| assert result.returncode == 0, result.stderr | |
| def test_segmentation_loads_the_shipped_decord_patch() -> None: | |
| patch = EVAL_TASK_ROOT / "qwenvl_decord_patch.py" | |
| evaluator = (EVAL_TASK_ROOT / "segmentation" / "eval_seg_vllm.py").read_text(encoding="utf-8") | |
| assert patch.is_file() | |
| assert "import qwenvl_decord_patch" in evaluator | |
| assert "Path(__file__).resolve().parents[1]," in evaluator | |