update to gpu

app.py

@@ -12,7 +12,7 @@ from model.tokenizer_utils import generate_custom_mask, prepare_tokenizer
 
 access_token = os.getenv("HF_TOKEN")
 model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
-device = 'cpu'
+device = 'cuda'
 
 model = LlamaskForCausalLM.from_pretrained(model_id, torch_dtype= torch.bfloat16, token=access_token)
 model = model.to(device)
@@ -48,7 +48,7 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Slider(minimum=1, maximum=128, value=32, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
     ],
 )