Update README.md

README.md

@@ -47,8 +47,14 @@ Below shows a code example on how to use this model
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-tokenizer = AutoTokenizer.from_pretrained("psmathur/orca_mini_v3_13b", use_fast=False)
-model = AutoModelForCausalLM.from_pretrained("psmathur/orca_mini_v3_13b", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("psmathur/orca_mini_v3_13b")
+model = AutoModelForCausalLM.from_pretrained(
+  "psmathur/orca_mini_v3_13b",
+  torch_dtype=torch.float16,
+  load_in_8bit=True,
+  low_cpu_mem_usage=True,
+  device_map="auto"
+)
 system_prompt = "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
 
 #generate text steps