Update app.py

app.py

@@ -51,13 +51,13 @@ tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 quantization_config_loading = GPTQConfig(bits=4, disable_exllama=True) #MR Added
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, device_map="auto", 
                                              trust_remote_code=True,
-                                             quantization_config=quantization_config_loading #MR Added
+                                             # quantization_config=quantization_config_loading #MR Added
                                              )
 
 # sentence transformers to be used in vector store
 embeddings = HuggingFaceEmbeddings(
       model_name="sentence-transformers/all-mpnet-base-v2", #Change MR
-      model_kwargs={'device': 'auto'}, #Change MR
+      model_kwargs={'device': 'cpu'}, 
       encode_kwargs={'normalize_embeddings': False}
   )