Update app.py

app.py

@@ -1,13 +1,14 @@
 from llama_cpp import Llama
 import gradio as gr
 
-# Load the GGUF model (quantized, small model)
+# Load GGUF model
 llm = Llama(
-    model_path="mental-health-chatbot-i1.Q4_K_M.gguf",  # change filename if using a different quant
+    model_path="mental-health-chatbot-i1.Q4_K_M.gguf",  # Make sure this filename matches exactly
     n_ctx=2048,
-    n_threads=4,  # adjust based on your Space CPU
+    n_threads=4,
 )
 
+# Chat logic
 def chat(message, history):
     full_prompt = ""
     for user, bot in history:
@@ -18,5 +19,7 @@ def chat(message, history):
     reply = output["choices"][0]["text"].strip()
     return reply
 
-# Simple chat UI
-gr.ChatInterface(fn=chat).launch()
+# Chat Interface
+gr.ChatInterface(fn=chat, title="Mental Health Llama Chatbot").launch(
+    server_name="0.0.0.0", server_port=7860
+)