Update app.py

app.py

@@ -5,8 +5,6 @@ from huggingface_hub import InferenceClient
 def respond(
     message,
     history: list[dict[str, str]],
-    system_message,
-    max_tokens,
     temperature,
     top_p,
     hf_token: gr.OAuthToken,
@@ -14,7 +12,18 @@ def respond(
     """
     For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    client = InferenceClient(token=hf_token.token, model="meta-llama/Llama-3.2-1B-Instruct")
+
+    system_message = (
+        "You are a 'Perspective Engine'. Analyze the user's input from three distinct emotional and logical angles. "
+        "Output your response in this exact Markdown format:\n\n"
+        "### 🟢 The Optimist\n"
+        "(Write an enthusiastic, positive analysis here)\n\n"
+        "### 🔴 The Pessimist\n"
+        "(Write a critical, risk-focused analysis here)\n\n"
+        "### 🔵 The Realist\n"
+        "(Write a balanced, factual conclusion here)"
+    )
 
     messages = [{"role": "system", "content": system_message}]
 
@@ -26,7 +35,6 @@ def respond(
 
     for message in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
@@ -47,8 +55,6 @@ chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,