Update app.py

app.py

@@ -30,6 +30,7 @@ MODEL_PATH = str(mistral_models_path)
 tokenizer = MistralTokenizer.from_file(os.path.join(MODEL_PATH, "tokenizer.model.v3"))
 model = Transformer.from_folder(MODEL_PATH)
 
+
 @spaces.GPU()
 def generate_response(message, history):
     # Convert history to the format expected by the model
@@ -46,13 +47,14 @@ def generate_response(message, history):
     tokens = tokenizer.encode_chat_completion(completion_request).tokens
     
     # Generate response
-    out_tokens, * = generate([tokens], model, max_tokens=256, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
+    out_tokens = generate([tokens], model, max_tokens=256, temperature=0.7, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)
     
     # Decode response
     result = tokenizer.instruct_tokenizer.tokenizer.decode(out_tokens[0])
     
     return result
 
+    
 # Gradio interface
 iface = gr.ChatInterface(
     generate_response,