test.py

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the model and tokenizer
model_name = "meta-llama/Llama-3.2-1B"  # Adjust the path if needed
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Input prompt
prompt = "Welcome to Saudi Travel and Tourism! How can I help you today?"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate output
outputs = model.generate(**inputs, max_new_tokens=50)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)

# Print response
print("LLaMA Response:", response)