import torch
from transformers import AutoTokenizer, AutoModel

MODEL = "faisalq/EgyBERT"

device = torch.device("cpu")


tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModel.from_pretrained(MODEL).to(device)

text = "إزيك يا صاحبي؟ عامل إيه؟"

inputs = tokenizer(text, return_tensors="pt").to(device)

with torch.no_grad():
    outputs = model(**inputs)

embedding = outputs.last_hidden_state.mean(dim=1)

print("Embedding shape:", embedding.shape)
print("Device:", embedding.device)