Update README.md

README.md

@@ -73,7 +73,40 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+
+```python
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForCausalLM 
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model = AutoModelForCausalLM.from_pretrained("AskUI/PTA-1", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
+processor = AutoProcessor.from_pretrained("AskUI/PTA-1", trust_remote_code=True)
+
+task_prompt = "<OPEN_VOCABULARY_DETECTION>"
+prompt = task_prompt + "description of the target element"
+
+image = Image.open("path to screenshot")
+
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
+
+generated_ids = model.generate(
+    input_ids=inputs["input_ids"],
+    pixel_values=inputs["pixel_values"],
+    max_new_tokens=1024,
+    do_sample=False,
+    num_beams=3,
+)
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
+
+parsed_answer = processor.post_process_generation(generated_text, task="<OPEN_VOCABULARY_DETECTION>", image_size=(image.width, image.height))
+
+print(parsed_answer)
+```
+
+
+
 
 ## Training Details