Update README.md

README.md

@@ -16,26 +16,23 @@ library_name: peft
 
 ## How to Get Started with the Model
 ```python
+from transformers import AutoModelForVision2Seq, AutoTokenizer, AutoProcessor
+from peft import PeftModel
+from PIL import Image
 import torch
-from peft import PeftModel, PeftConfig
-from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load base model
-base_model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
-base_model = AutoModelForCausalLM.from_pretrained(base_model_id)
+model = PeftModel.from_pretrained(
+    AutoModelForVision2Seq.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct", device_map="auto", load_in_4bit=True),
+    "pdufour/Llama-3.2-11B-Vision-WebSight"
+)
+tokenizer = AutoTokenizer.from_pretrained("pdufour/Llama-3.2-11B-Vision-WebSight")
+processor = AutoProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision-Instruct")
 
-# Initialize model with adapter weights
-model = PeftModel.from_pretrained(base_model, "pdufour/Llama-3.2-11B-Vision-WebSight")
-tokenizer = AutoTokenizer.from_pretrained(base_model_id)
+inputs = processor(text="Generate code for a web page that looks exactly like this. <|image|>", images=Image.open("fashion.jpg"), return_tensors="pt").to(model.device)
 
-# Prepare input 
-image_path = "path_to_your_image.jpg"
-text = "Generate code for a web page that looks exactly like this"
+with torch.no_grad():
+    outputs = model.generate(input_ids=inputs['input_ids'], max_new_tokens=4096, do_sample=True, temperature=0.7, top_p=0.9)
 
-inputs = processor(images=image_path, text=text, return_tensors="pt")
-
-# Generate response
-outputs = model.generate(**inputs)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```