Update app.py

app.py

@@ -17,7 +17,7 @@ model = LlamaForCausalLM.from_pretrained(
     load_in_8bit=True,
     device_map="auto") #low_cpu_mem_usage=True)
 
-#model = model.to('cuda')
+model = model.to('cuda')
 
 
 def add_text(history, text):
@@ -68,7 +68,7 @@ def generateresponse(history, task):
         PROMPT,
         return_tensors="pt",
     ) 
-    input_ids = inputs["input_ids"]#.cuda()
+    input_ids = inputs["input_ids"].cuda()
 
     generation_config = GenerationConfig(
         temperature=0.6,