main.py

import os

from ctransformers import AutoModelForCausalLM
from fastapi import FastAPI
from pydantic import BaseModel
import requests
#
# llm = AutoModelForCausalLM.from_pretrained("zephyr-7b-beta.Q4_K_S.gguf",
# model_type='mistral',
# max_new_tokens = 1096,
# threads = 3,
# )

#Pydantic object
class validation(BaseModel):
    prompt: str
#Fast API

app = FastAPI()
file_name = "zephyr-7b-beta.Q4_K_S.gguf"

if not os.path.exists(file_name):
    print("Downloading model...")
    url = "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/resolve/main/zephyr-7b-beta.Q4_K_S.gguf"
    response = requests.get(url)
    print(response.status_code)
    with open(file_name, 'wb') as file:
        file.write(response.content)


@app.post("/llm_on_cpu")
async def stream(item: validation):
    system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
    E_INST = "</s>"
    user, assistant = "<|user|>", "<|assistant|>"
    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
    # return llm(prompt)
    return prompt