Update README.md

the original example code included two BOS tokens during inference.

modified it so that only one BOS token is included.

README.md

@@ -103,7 +103,7 @@ prompt = processor.tokenizer.apply_chat_template(
 )
 url = "https://www.ilankelman.org/stopsigns/australia.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
-inputs = processor(text=prompt, images=image, return_tensors="pt")
+inputs = processor(text=prompt[5:], images=image, return_tensors="pt")
 
 # Generate
 generate_ids = model.generate(**inputs, max_length=30)