---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- multimodal
- aria
---
<!-- <p align="center">
  <br>Aria</br>
</p>  -->

This is a fork of the [rhymes-ai/Aria](https://huggingface.co./rhymes-ai/Aria) model. The only modification is replacing [grouped GEMM](https://github.com/tgale96/grouped_gemm) with a sequential MLP. In this configuration, each expert is implemented as a `torch.nn.Linear` layer executed in sequence. This adjustment simplifies quantization with current open-source libraries, which are optimized for `nn.Linear` layers. 

While the sequential MLP approach aids in easier quantization, using grouped GEMM provides the advantage of faster inference speed.


## Quick Start
### Installation
```
pip install transformers==4.45.0 accelerate==0.34.1 sentencepiece==0.2.0 torchvision requests torch Pillow
pip install flash-attn --no-build-isolation
```

### Inference

```python
import requests
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor

model_id_or_path = "rhymes-ai/Aria-sequential_mlp"

model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)

processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)

image_path = "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"

image = Image.open(requests.get(image_path, stream=True).raw)

messages = [
    {
        "role": "user",
        "content": [
            {"text": None, "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(model.dtype)
inputs = {k: v.to(model.device) for k, v in inputs.items()}

with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
    output = model.generate(
        **inputs,
        max_new_tokens=500,
        stop_strings=["<|im_end|>"],
        tokenizer=processor.tokenizer,
        do_sample=True,
        temperature=0.9,
    )
    output_ids = output[0][inputs["input_ids"].shape[1]:]
    result = processor.decode(output_ids, skip_special_tokens=True)

print(result)
```