Update app.py

app.py

@@ -15,7 +15,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 if torch.cuda.is_available():
     model_id = "BramVanroy/GEITje-ultra"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    model = AutoModelForCausalLM.from_pretrained(model_id, load_in_8bit=True, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 
@@ -80,14 +80,14 @@ chat_interface = gr.ChatInterface(
             minimum=0.05,
             maximum=2,
             step=0.05,
-            value=0.2,
+            value=1.0,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",
             minimum=0.05,
             maximum=1.0,
             step=0.05,
-            value=0.9,
+            value=1.0,
         ),
         gr.Slider(
             label="Top-k",