def prompt_hf(request, model="haesleinhuepf/gemma-2b-it-bia-proof-of-concept2"):
    global prompt_hf
    import transformers
    import torch
    
    if prompt_hf._pipeline is None:    
        prompt_hf._pipeline = transformers.pipeline(
            "text-generation", model=model, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
        )
    
    return prompt_hf._pipeline(request)[0]['generated_text']
prompt_hf._pipeline = None

prompt_hf("What is the capital of France?")