add space

app.py

@@ -1,3 +1,4 @@
+import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 from peft import PeftModel
@@ -22,6 +23,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 # 2) HuggingFace에서 LoRA 가중치 다운로드 & 적용
 model = PeftModel.from_pretrained(base_model, "JunHwi/Joseon-Qwen")
 
+@spaces.GPU
 def generate(prompt, model, max_new_tokens=200):
     model.eval()
     messages = [{"role": "user", "content": prompt}]

requirements.txt

@@ -4,3 +4,4 @@ peft
 accelerate
 bitsandbytes
 gradio
+spaces