Update app.py

app.py

@@ -4,10 +4,10 @@ from ctransformers import AutoModelForCausalLM
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-7B-uncensored-GGUF", model_file="WizardLM-7B-uncensored.Q4_K_M.gguf", model_type="llama", stream=True)
-
+list = []
 def generate_response(message):
     for text in llm(message):
-        toe = "".join(text)
+        toe = list.join(text)
         yield toe