main.py

from ctransformers import AutoModelForCausalLM
from fastapi import FastAPI
from pydantic import BaseModel

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()

@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 = "", ""
    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
    return await llm(prompt)  # Making the call asynchronous