Update app.py

app.py

@@ -3,13 +3,14 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
 import shutil
+import spaces
 
 model_name = "minoD/JURAN"
 
 # モデルのロード
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    device_map="auto",
+    device_map="cpu",
     torch_dtype=torch.float16
     
 )
@@ -32,6 +33,7 @@ def generate_prompt(F):
 
 # テキスト生成関数の定義
 def generate2(F=None, maxTokens=256):
+    model.to("cuda")
     # 推論
     prompt = generate_prompt(F)
     input_ids = tokenizer(prompt,
@@ -81,4 +83,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-     iface.launch(share=True)
+    iface.launch()