models.py

import torch
from transformers import pipeline

def get_tiny_llama():
    pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.float16, device_map="auto")
    return pipe

def response_tiny_llama(
        pipe=None,
        content="How many helicopters can a human eat in one sitting?"
        ):
    # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
    messages = [
        {
            "role": "system",
            "content": "You are a friendly chatbot who always responds in the style of a pirate",
        },
        {"role": "user", "content": content},
    ]
    prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    outputs = pipe(prompt, max_new_tokens=32, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)

    return outputs[0]['generated_text'].split('<|assistant|>')[1]