---
license: apache-2.0
---

# OFA-Medium
This is the **medium** version of OFA pretrained model. OFA is a unified multimodal pretrained model that unifies modalities (i.e., cross-modality, vision, language) and tasks (e.g., image generation, visual grounding, image captioning, image classification, text generation, etc.) to a simple sequence-to-sequence learning framework.

To use it in Transformers, please refer to https://github.com/OFA-Sys/OFA/tree/feature/add_transformers and download the directory of transformers. After installation, you can use it as shown below:

```
>>> from PIL import Image
>>> from torchvision import transforms
>>> from transformers import OFATokenizer, OFAForConditionalGeneration

>>> mean, std = [0.5, 0.5, 0.5], [0.5, 0.5, 0.5]
>>> resolution = 256
>>> patch_resize_transform = transforms.Compose([
        lambda image: image.convert("RGB"),
        transforms.Resize((resolution, resolution), interpolation=Image.BICUBIC),
        transforms.ToTensor(), 
        transforms.Normalize(mean=mean, std=std)
    ])

>>> model = OFAForConditionalGeneration.from_pretrained(ckpt_dir)
>>> tokenizer = OFATokenizer.from_pretrained(ckpt_dir)

>>> txt = " what is the description of the image?"
>>> inputs = tokenizer([txt], max_length=1024, return_tensors="pt")["input_ids"]
>>> img = Image.open(path_to_image)
>>> patch_img = patch_resize_transform(img).unsqueeze(0)

>>> gen = model.generate(inputs, patch_img=patch_img, num_beams=4)
>>> print(tokenizer.decode(gen, skip_special_tokens=True, clean_up_tokenization_spaces=False))
```