from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
from multiprocessing import freeze_support


if __name__ == '__main__':
    freeze_support()
    # Initialize the tokenizer
    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")

    # Pass the default decoding hyperparameters of Qwen3-8B.
    # max_tokens is for the maximum length for generation.
    sampling_params = SamplingParams(temperature=0.7, top_p=0.8, repetition_penalty=1.05, max_tokens=512)

    # Input the model name or path. Can be GPTQ or AWQ models.
    llm = LLM(model="Qwen/Qwen3-8B" , tensor_parallel_size=4)

    # Prepare your prompts
    '''
    prompt = "Give me a short introduction to large language models."
    messages = [
        {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    '''
    prompt = "How many r's are in the word \"strawberry\""
    messages = [
        {"role": "user", "content": prompt}
    ]

    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    # generate outputs
    outputs = llm.generate([text], sampling_params)

    # Print the outputs.
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Generated text: {generated_text!r}")