pip install "transformers>=4.48.0" accelerate sentencepiece torchvision requests torch Pillow
pip install flash-attn --no-build-isolation

# For better inference performance, you can install grouped-gemm, which may take 3-5 minutes to install
pip install grouped_gemm==0.1.6

import requests
import torch
from PIL import Image

from transformers import AriaProcessor, AriaForConditionalGeneration


model_id_or_path = "rhymes-ai/Aria"
model = AriaForConditionalGeneration.from_pretrained(
    model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16
)

processor = AriaProcessor.from_pretrained(model_id_or_path)

image = Image.open(requests.get("http://images.cocodataset.org/val2017/000000039769.jpg", stream=True).raw)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image"},
            {"text": "what is the image?", "type": "text"},
        ],
    }
]

text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=text, images=image, return_tensors="pt")
inputs['pixel_values'] = inputs['pixel_values'].to(torch.bfloat16)
inputs.to(model.device)

output = model.generate(
    **inputs,
    max_new_tokens=15,
    stop_strings=["<|im_end|>"],
    tokenizer=processor.tokenizer,
    do_sample=True,
    temperature=0.9,
)
output_ids = output[0][inputs["input_ids"].shape[1]:]
response = processor.decode(output_ids, skip_special_tokens=True)
print(response)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"}
            {"type": "text", "text": "what is the image?"},
        ],
    },
]

inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt")
ipnuts = inputs.to(model.device, torch.bfloat16)

output = model.generate(
    **inputs,
    max_new_tokens=15,
    stop_strings=["<|im_end|>"],
    tokenizer=processor.tokenizer,
    do_sample=True,
    temperature=0.9,
)
output_ids = output[0][inputs["input_ids"].shape[1]:]
response = processor.decode(output_ids, skip_special_tokens=True)
print(response)

@article{aria,
  title={Aria: An Open Multimodal Native Mixture-of-Experts Model}, 
  author={Dongxu Li and Yudong Liu and Haoning Wu and Yue Wang and Zhiqi Shen and Bowen Qu and Xinyao Niu and Guoyin Wang and Bei Chen and Junnan Li},
  year={2024},
  journal={arXiv preprint arXiv:2410.05993},
}