Update app.py

app.py

@@ -24,7 +24,7 @@ def load_model(model_name):
         from langchain.llms import CTransformers
 
         model =  CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", 
-                    model_file = 'llama-2-7b-chat.ggmlv3.q2_K.bin', 
+                    model_file = 'llama-2-7b-chat.ggmlv3.q4_0.bin', #'llama-2-7b-chat.ggmlv3.q4_K.bin', 
                     model_type='llama', gpu_layers=0) # config={"context_length":2048,})
         tokenizer = None