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
| """Stable prompt and media identities used for sampling and leakage checks.""" | |
| from __future__ import annotations | |
| import hashlib | |
| import json | |
| import os | |
| import unicodedata | |
| from collections.abc import Mapping | |
| from pathlib import Path | |
| from typing import Any | |
| from .schema import media_paths, normalize_text | |
| def normalized_media_anchor(path: str) -> str: | |
| """Return a case-normalized lexical identity for one local media path.""" | |
| normalized = os.path.normpath(str(path)).replace("\\", "/") | |
| return unicodedata.normalize("NFKC", normalized).casefold() | |
| def media_anchors(record: Mapping[str, Any]) -> tuple[str, ...]: | |
| """Return exact normalized media anchors for cap enforcement.""" | |
| return tuple(sorted({normalized_media_anchor(path) for path in media_paths(record)})) | |
| def media_leakage_tokens(record: Mapping[str, Any]) -> frozenset[str]: | |
| """Return exact and basename tokens for fail-closed media comparisons.""" | |
| tokens: set[str] = set() | |
| for anchor in media_anchors(record): | |
| path = Path(anchor) | |
| name = normalize_text(path.name) | |
| stem = normalize_text(path.stem) | |
| tokens.add(f"path:{anchor}") | |
| if name: | |
| tokens.add(f"name:{name}") | |
| if stem: | |
| tokens.add(f"stem:{stem}") | |
| return frozenset(tokens) | |
| def prompt_identity(record: Mapping[str, Any]) -> str: | |
| """Hash what is asked and its media, intentionally excluding the answer.""" | |
| payload = { | |
| "media": media_anchors(record), | |
| "problem": normalize_text(record.get("problem")), | |
| "problem_type": normalize_text(record.get("problem_type")), | |
| } | |
| encoded = json.dumps( | |
| payload, | |
| ensure_ascii=False, | |
| sort_keys=True, | |
| separators=(",", ":"), | |
| ).encode("utf-8") | |
| return hashlib.sha256(encoded).hexdigest() | |
| def stable_rank(seed: int, namespace: str, identity: str) -> int: | |
| """Create a process-independent deterministic rank.""" | |
| payload = f"{seed}|{namespace}|{identity}".encode("utf-8") | |
| return int.from_bytes(hashlib.sha256(payload).digest(), "big") | |