from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-4B",
    dtype="auto",        # picks bf16/fp16 from the model config
    device_map="auto",
)

# Build the prompt with the model's own chat template
messages = [
    {"role": "user", "content": "Hello! How are you?"}
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)

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

# Only decode the newly generated tokens, not the prompt
response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
print(response)