main.py

from fastapi import FastAPI
from pydantic import BaseModel
from huggingface_hub import InferenceClient
import uvicorn
import os
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    TextIteratorStreamer,
)

app = FastAPI()

HF_TOKEN = os.environ["HF_TOKEN"]

model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct",
                                            device_map="auto",
                                            token=HF_TOKEN
                                            )

class Item(BaseModel):
    prompt: str
    system_prompt: str
    temperature: float = 0.0
    max_new_tokens: int = 1048
    top_p: float = 0.15
    repetition_penalty: float = 1.0


@app.post("/generate/")
async def generate_text(item: Item):
    return {"response": item.prompt}