How to generate multiple text completions per prompt (like vLLM) using HuggingFace Transformers Pipeline without triggering an error?

Beginners
3

error:

error: ` Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.`

fix:

def pipeline_tests_():
    print(f'\n--> pipeline_tests_()')
    import torch
    from transformers import pipeline

    # pipe = pipeline(model="gpt2", device_map="auto", model_kwargs={"load_in_8bit": True})
    pipe = pipeline(model="gpt2", device_map="auto", model_kwargs={"load_in_4bit": True})

    # output = pipe("This is a cool example!", do_sample=True, top_p=0.95, temperature=0.8, max_length=50)
    output = pipe("This is a cool example!", do_sample=True, top_p=0.95, temperature=0.8, max_length=50, truncation=True)
    print(f'\n{output=}')
    print(f'{len(output)=}')

    output = pipe("This is a cool example!", do_sample=True, top_p=0.95, temperature=0.8, max_length=50, num_return_sequences=4, truncation=True)
    print(f'\n{output=}')
    print(f'{len(output)=}')

    output = pipe("This is a cool example!", do_sample=False, top_p=0.95, temperature=0.8, max_length=50, num_return_sequences=4, num_beams=5, truncation=True)
    print(f'\n{output=}')
    print(f'{len(output)=}')

    print()