Update README.md

README.md

@@ -5,8 +5,33 @@ language:
 library_name: transformers
 inference: False
 ---
-## Sharded BLIP-2 Model Card
+## Sharded BLIP-2 Model Card - flan-t5-xl
 
-This is a sharded version of the [BLIP-2 Model Card](https://huggingface.co/models/Salesforce/blip2-flan-t5-xl) which leverages [Flan T5-xl](https://huggingface.co/google/flan-t5-xl) for image-to-text tasks such as image captioning and visual question answering.
+This is a sharded version of the [blip2-flan-t5-xl](https://huggingface.co/models/Salesforce/blip2-flan-t5-xl) which leverages [Flan T5-xl](https://huggingface.co/google/flan-t5-xl) for image-to-text tasks such as image captioning and visual question answering.
+
+Refer to the [original model card](https://huggingface.co/models/Salesforce/blip2-flan-t5-xl) for more details about the model description, intended uses, and limitations, as well as instructions for how to use the model on CPU and GPU in different precisions.
+
+## Usage
+
+Refer to the original model card for details or see [this blog post](https://huggingface.co/blog/blip-2#using-blip-2-with-hugging-face-transformers). Here is how you can use it on CPU:
+
+
+```python
+import requests
+from PIL import Image
+from transformers import BlipProcessor, Blip2ForConditionalGeneration
+
+model_name = "Salesforce/blip2-flan-t5-xl")
+processor = BlipProcessor.from_pretrained(model_name)
+model = Blip2ForConditionalGeneration.from_pretrained(model_name)
+
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+question = "how many dogs are in the picture?"
+inputs = processor(raw_image, question, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+```
 
-Refer to the [original model card](https://huggingface.co/models/Salesforce/blip2-flan-t5-xl) for more details about the model description, intended uses, and limitations, as well as instructions for how to use the model on CPU and GPU in different precisions.