def generate_text(model, input_text, max_length=50):
    input_ids = tokenizer.encode(input_text, return_tensors='pt').to(device)
    output = model.generate(inputs=input_ids,
                            max_length=max_length,
                            do_sample=True,
                            top_k=30,
                            pad_token_id=tokenizer.eos_token_id,
                            attention_mask=input_ids.new_ones(input_ids.shape))
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Generate text with original and quantized models
original_text = generate_text(model, "I have a dream")
absmax_text   = generate_text(model_abs, "I have a dream")
zp_text       = generate_text(model_zp, "I have a dream")

print(f"Original model:n{original_text}")
print("-" * 50)
print(f"Absmax model:n{absmax_text}")
print("-" * 50)
print(f"Zeropoint model:n{zp_text}")