Update app.py

app.py

@@ -17,16 +17,11 @@ def format_prompt(message, history):
 def generate(
     prompt, history, temperature=0.9, max_new_tokens=4000, top_p=0.95, repetition_penalty=1.0,
 ):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
     generate_kwargs = dict(
-        temperature=temperature,
+        temperature=0.9,
         max_new_tokens=4000,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
+        top_p=0.9,
+        repetition_penalty=1.0,
         do_sample=True,
         seed=42,
     )
@@ -41,37 +36,6 @@ def generate(
         yield output
     return output
 
-
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
-
 css = """
   #mkd {
     height: 500px; 
@@ -83,8 +47,7 @@ css = """
 with gr.Blocks(css=css) as demo:
     gr.HTML("<h1><center>Mistral 7B Instruct<h1><center>")
     gr.ChatInterface(
-        generate,
-        additional_inputs=additional_inputs,
+        generate
     )
 
 demo.queue().launch(debug=True)