Update app.py

app.py

@@ -72,6 +72,44 @@ def inference(model_name, text, input):
 def choose_model(name):
     return load_model(name), load_tokenizer(name)
 
+with gr.Accordion(label="Parameters", open=False, elem_id="parameters-accordion"):
+    temperature = gr.Slider(
+        label="Temperature",
+        value=0.7,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.1,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    )
+    top_p = gr.Slider(
+        label="Top-p (nucleus sampling)",
+        value=0.9,
+        minimum=0.0,
+        maximum=1,
+        step=0.05,
+        interactive=True,
+        info="Higher values sample more low-probability tokens",
+    )
+    max_new_tokens = gr.Slider(
+        label="Max new tokens",
+        value=1024,
+        minimum=0,
+        maximum=2048,
+        step=4,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    )
+    repetition_penalty = gr.Slider(
+        label="Repetition Penalty",
+        value=1.2,
+        minimum=0.0,
+        maximum=10,
+        step=0.1,
+        interactive=True,
+        info="The parameter for repetition penalty. 1.0 means no penalty.",
+    )
+
 io = gr.Interface(
     inference, 
     inputs = [