question_paper.py

import transformers
import torch

from fastapi import FastAPI

from transformers import AutoModelForCausalLM, AutoTokenizer

app = FastAPI()
@app.get("/")
def llama():
    tokenizer = AutoTokenizer.from_pretrained("Upstage/SOLAR-10.7B-v1.0")
    model = AutoModelForCausalLM.from_pretrained("Upstage/SOLAR-10.7B-v1.0", device_map="auto", torch_dtype=torch.float16,)
    text = "Hi, my name is "
    inputs = tokenizer(text, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=64)
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

    return tokenizer.decode(outputs[0], skip_special_tokens=True)