from transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig
import torch

مسح ذاكرة التخزين المؤقت لـ CUDA (Clear CUDA cache)

if torch.cuda.is_available():
torch.cuda.empty_cache()
print("CUDA cache cleared.")

messages = [
{
"role": "user",
"content": [
{
"type": "image",
"url": "https://raw.githubusercontent.com/zheny2751-dotcom/UI2Code-N/main/assets/example.png"
},
{
"type": "text",
"text": "Based on the domtree and the page screenshot, please identify which interactive components in the image require interaction. Please note that if similar buttons have been clicked on similar pages in the past, do not click them again, and also do not select buttons that are obscured on the page."
}
]
}
]
processor = AutoProcessor.from_pretrained("zai-org/WebVIA-Agent", use_fast=True)

تعريف إعدادات التكميم 4-بت (Define 4-bit quantization settings)

quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True
)

model = AutoModelForImageTextToText.from_pretrained(
pretrained_model_name_or_path="zai-org/WebVIA-Agent",
dtype=torch.bfloat16, # تم تغيير torch_dtype إلى dtype
device_map="auto", # تغيير device_map إلى "auto" للسماح بالتوزيع التلقائي
quantization_config=quantization_config # استخدام BitsAndBytesConfig هنا
)
inputs = processor.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_dict=True,
return_tensors="pt"
).to(model.device)
generated_ids = model.generate(**inputs, max_new_tokens=1)
output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
print(output_text)