added low memory mode for llm configuration on CPU

app.py

@@ -31,7 +31,12 @@ embeddings = HuggingFaceHubEmbeddings()
 
 model_id = "HuggingFaceH4/zephyr-7b-beta"
 # model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    device_map="auto",
+    low_cpu_mem_usage=True
+)
+
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 tokenizer.use_default_system_prompt = False