Update app.py

app.py

@@ -19,7 +19,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "Sakalti/Saba1.5-Pro"
+model_id = "Sakalti/magro-7B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -89,14 +89,14 @@ demo = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            value=0.7,
         ),
         gr.Slider(
             label="Top-p (nucleus sampling)",
             minimum=0.05,
             maximum=1.0,
             step=0.05,
-            value=0.9,
+            value=0.95,
         ),
         gr.Slider(
             label="Top-k",