update app.py

app.py

@@ -3,7 +3,6 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
 def load_model():
-    # Download the model from HuggingFace
     repo_id = "forestav/gguf_lora_model"
     model_file = "unsloth.F16.gguf"  
     
@@ -12,7 +11,8 @@ def load_model():
         filename=model_file
     )
     
-    # Initialize the model
+    print(f"Loading model from: {local_path}")
+    
     model = Llama(
         model_path=local_path,
         n_ctx=2048,
@@ -22,7 +22,6 @@ def load_model():
     return model
 
 def generate_response(message, history):
-    # Generate response
     response = model.create_chat_completion(
         messages=[
             {"role": "user", "content": message}
@@ -35,9 +34,11 @@ def generate_response(message, history):
     return response['choices'][0]['message']['content']
 
 # Load model globally
+print("Starting model loading...")
 model = load_model()
+print("Model loaded successfully!")
 
-# Create Gradio interface with updated parameters
+# Create Gradio interface
 demo = gr.ChatInterface(
     fn=generate_response,
     title="Your GGUF Model Chat",
@@ -45,5 +46,9 @@ demo = gr.ChatInterface(
     examples=["Continue the fibonacci sequence: 1, 1, 2, 3, 5, 8,"]
 )
 
-if __name__ == "__main__":
-    demo.launch()
+# Add proper Gradio launch configuration for Spaces
+demo.launch(
+    server_name="0.0.0.0",  # Necessary for Spaces
+    server_port=7860,       # Standard port for Spaces
+    share=False            # Don't need share link in Spaces
+)