from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-12b-it")

model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-3-12b-it",
    device_map="auto",
    torch_dtype=torch.float16
)

# Prepare input
messages = [
    {"role": "user", "content": "Hello! How are you?"}
]
input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

# Generate response
outputs = model.generate(
    input_ids,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)