Update app.py

app.py

@@ -31,7 +31,7 @@ llm = HuggingFaceLLM(
     model_name="NousResearch/Llama-2-7b-hf",
     device_map="auto",
     # uncomment this if using CUDA to reduce memory usage
-    model_kwargs={"torch_dtype": torch.float16 , "load_in_8bit":False}
+    # model_kwargs={"torch_dtype": torch.float16 , "load_in_8bit":False}
 )
 
 from langchain.embeddings.huggingface import HuggingFaceEmbeddings