Update app.py

app.py

@@ -9,7 +9,9 @@ model_name = "minoD/JURAN"
 # モデルのロード
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    device_map="cpu"
+    device_map="auto",
+    torch_dtype=torch.float16
+    
 )
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
@@ -35,7 +37,7 @@ def generate2(F=None, maxTokens=256):
     input_ids = tokenizer(prompt,
                           return_tensors="pt",
                           truncation=True,
-                          add_special_tokens=False).input_ids
+                          add_special_tokens=False).input_ids.to(model.device)
     outputs = model.generate(
         input_ids=input_ids,
         max_new_tokens=maxTokens,