Update app.py

app.py

@@ -72,12 +72,11 @@ def generate(
         {"input_ids": input_ids},
         streamer=streamer,
         max_new_tokens=max_new_tokens,
-        do_sample=True,
+        do_sample=False if (temperature == 0 or top_k == 1) else True,
         top_p=top_p,
         top_k=top_k,
         temperature=temperature,
         num_beams=1,
-        repetition_penalty=0.0,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
@@ -108,14 +107,14 @@ chat_interface = gr.ChatInterface(
             minimum=0.1,
             maximum=4.0,
             step=0.1,
-            value=0.6,
+            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",