Update app.py

app.py

@@ -13,6 +13,7 @@ model_name = model_id.split('/')[-1]
 title = f"🇩🇪 {model_name}"
 description = f"Chat with <a href=\"https://huggingface.co/{model_id}\">{model_name}</a> in GGUF format ({quant})!"
 
+print("loading model")
 # Initialize the LLM
 llm = Llama(model_path="model.gguf",
             n_ctx=32768,
@@ -20,7 +21,7 @@ llm = Llama(model_path="model.gguf",
             chat_format=chat_template)
 
 # Function for streaming chat completions
-def chat_stream_completion(message, history, system_prompt):
+def chat_stream_completion(message, history):
     #messages_prompts = [{"role": "system", "content": system_prompt}]
     messages_prompts = []
     for human, assistant in history:
@@ -39,6 +40,7 @@ def chat_stream_completion(message, history, system_prompt):
             message_repl = message_repl + chunk['choices'][0]["delta"]["content"]
         yield message_repl
 
+print("starting gradio")
 # Gradio chat interface
 gr.ChatInterface(
     fn=chat_stream_completion,