Omni-R1-Zero

import torch
from PIL import Image
from transformers import ChameleonProcessor, ChameleonForConditionalGeneration

# 1) Import & load
model_id = "ModalityDance/Omni-R1-Zero"  # or a local checkpoint path
processor = ChameleonProcessor.from_pretrained(model_id)
model = ChameleonForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

# 2) Prepare a single input
prompt = "You are a helpful assistant.\nUser: Which of these would appear shinier when polished? A. Metal spoon B. Wooden spoon\nThink with images first, the image reasoning process and answer are enclosed within <reserved12856> <reserved12857> and <reserved12866> <reserved12867> XML tags, respectively.\nAssistant:"

inputs = processor(
    prompt,
    padding=False,
    return_for_text_completion=True,
    return_tensors="pt",
).to(model.device)

# 3) Call the model
outputs = model.generate(
    **inputs,
    max_length=4096,
    do_sample=True,
    temperature=1.0,
    top_p=0.9,
    pad_token_id=1,
    multimodal_generation_mode="unrestricted",
)

# 4) Get results
text = processor.batch_decode(outputs, skip_special_tokens=False)[0]
print(text)