main.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# 무료 모델 선택 (Mistral 7B)
model_name = "mistralai/Mistral-7B-Instruct-v0.1"

# 토크나이저 및 모델 불러오기
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")

def chat(user_input):
    inputs = tokenizer(user_input, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
    outputs = model.generate(**inputs, max_length=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# 테스트 실행
print(chat("Hello, how are you?"))