Update app.py

app.py

@@ -26,16 +26,17 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 print("loading the LLM......................................")
 
-# llm = LlamaCpp(
-#     model_path="./llama-2-7b-chat.Q3_K_S.gguf",
-#     temperature = 0.2,
-#     n_ctx=2048,
-#     f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls
-#     max_tokens = 500,
-#     callback_manager=callback_manager,
-#     verbose=True,
-# )
+llm = LlamaCpp(
+    model_path="./llama-2-7b-chat.Q3_K_S.gguf",
+    temperature = 0.2,
+    n_ctx=2048,
+    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls
+    max_tokens = 500,
+    callback_manager=callback_manager,
+    verbose=True,
+)
 
+'''
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
                                            model_file="llama-2-7b-chat.Q3_K_S.gguf", 
                                            model_type="llama", 
@@ -44,7 +45,7 @@ llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF",
                                            max_new_tokens = 300,
                                            )
 
-
+'''
 
 print("LLM loaded........................................")
 print("################################################################")