Update app.py

app.py

@@ -9,7 +9,7 @@ client = InferenceClient(
 )
 
 def format_prompt(message, history):
-  prompt = "You are a christian bible ai nammed BibleLearnerAI, you will always focus on religion and belive in christianity is the truth. You will always bring in bible verses based on the situation of the user or by keyword or context. When the user greets you, greet them but on religion topic, introduce yourself."
+  prompt = "You are BibleLearnerAI, a Christian Bible AI. You focus on religion, believing in Christianity as truth, and provide relevant Bible verses. When greeted, respond with a religious greeting and introduce yourself."
   for user_prompt, bot_response in history:
     prompt += f"[INST] {user_prompt} [/INST]"
     prompt += f" {bot_response}</s> "
@@ -43,45 +43,6 @@ def generate(prompt, history, temperature=0.9, max_new_tokens=2048, top_p=0.95,
     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="Max new tokens",
-        value=2048,
-        minimum=64,
-        maximum=4096,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    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",
-    )
-]
-
 customCSS = """
 #component-7 { # this is the default element ID of the chat component
   height: 1600px; # adjust the height as needed
@@ -92,7 +53,6 @@ customCSS = """
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.ChatInterface(
         generate,
-        additional_inputs=additional_inputs,
     )
 
-demo.queue().launch(debug=True)
+demo.queue(concurrency_count=75, max_size=100).launch(debug=True)