Update README.md

README.md

@@ -2,10 +2,18 @@
 license: apache-2.0
 ---
 
-# OFA-Medium
+# OFA-tiny
 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:
+The directory includes 4 files, namely `config.json` which consists of model configuration, `vocab.json` and `merge.txt` for our OFA tokenizer, and lastly `pytorch_model.bin` which consists of model weights. There is no need to worry about the mismatch between Fairseq and transformers, since we have addressed the issue yet. 
+
+To use it in transformers, please refer to https://github.com/OFA-Sys/OFA/tree/feature/add_transformers. Install the transformers and download the models as shown below.
+```
+git clone --single-branch --branch feature/add_transformers https://github.com/OFA-Sys/OFA.git
+pip install OFA/transformers/
+it clone https://huggingface.co/OFA-Sys/OFA-medium
+```
+After, refer the path to OFA-medium to `ckpt_dir`, and prepare an image for the testing example below. Also, ensure that you have pillow and torchvision in your environment. 
 
 ```
 >>> from PIL import Image
@@ -29,6 +37,6 @@ To use it in Transformers, please refer to https://github.com/OFA-Sys/OFA/tree/f
 >>> 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))
+>>> gen = model.generate(inputs, patch_images=patch_img, num_beams=4)
+>>> print(tokenizer.batch_decode(gen, skip_special_tokens=True))
 ```