Update app.py

app.py

@@ -15,7 +15,8 @@ model_name = "decapoda-research/llama-7b-hf"
 adapters_name = 'timdettmers/guanaco-7b'
 # print(f"Starting to load the model {model_name} into memory")
 m = AutoModelForCausalLM.from_pretrained(
-    model_name)
+    model_name,
+    load_in_4bit=True)
 m = PeftModel.from_pretrained(m, adapters_name)
 m = m.merge_and_unload()
 tok = LlamaTokenizer.from_pretrained(model_name)