Update README.md

README.md

@@ -46,29 +46,28 @@ pip install git+https://github.com/huggingface/optimum-intel.git
 from PIL import Image 
 import requests 
 from optimum.intel.openvino import OVModelForVisualCausalLM
-from transformers import AutoTokenizer, TextStreamer
+from transformers import AutoProcessor, TextStreamer
 
 model_id = "OpenVINO/pixtral-12b-int4-ov"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-
+processor = AutoProcessor.from_pretrained(model_dir)
 ov_model = OVModelForVisualCausalLM.from_pretrained(model_id, trust_remote_code=True)
-prompt = "What is unusual on this picture?"
+
+question = "What is unusual in this picture?"
+messages = [
+    {"role": "user", "content": [{"type": "text", "content": question}, {"type": "image"}]},
+]
+text = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+
 
 url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
 image = Image.open(requests.get(url, stream=True).raw)
 
-inputs = ov_model.preprocess_inputs(text=prompt, image=image, tokenizer=tokenizer, config=ov_model.config)
-
-generation_args = { 
-    "max_new_tokens": 100, 
-    "streamer": TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-} 
 
-generate_ids = ov_model.generate(**inputs, **generation_args)
+inputs = processor(text=text, images=[resize_with_aspect_ratio(raw_image)], return_tensors="pt")
+streamer = TextStreamer(processor.tokenizer, skip_prompt=True, skip_special_tokens=True)
 
-generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
-response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True)[0]
+output = ov_model.generate(**inputs, do_sample=False, max_new_tokens=100, temperature=None, top_p=None, streamer=streamer)
 
 ```