OriOn-Qwen-SR1

import torch
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor

model_id = "lightonai/OriOn-Qwen-SR1"
device = "cuda" if torch.cuda.is_available() else "cpu"

model = Qwen3VLForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_id)

# Multi-page document QA with <cot> reasoning
messages = [
    {"role": "system", "content": "<cot>"},
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "page1.png"},
            {"type": "image", "url": "page2.png"},
            # ... add all document pages
            {"type": "text", "text": "What are the key findings discussed across this document?"},
        ],
    },
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(device)

output_ids = model.generate(**inputs, max_new_tokens=4096)
generated_ids = output_ids[0, inputs["input_ids"].shape[1]:]
print(processor.decode(generated_ids, skip_special_tokens=True))