Update README with chat template examples

README.md

@@ -111,12 +111,12 @@ if torch.cuda.is_available():
 else:
     torch.set_default_device("cpu")
     
-model = transformers.AutoModelForCausalLM.from_pretrained("./Orca-2-13b", device_map='auto')
+model = transformers.AutoModelForCausalLM.from_pretrained("microsoft/Orca-2-13b", device_map='auto')
 
 # https://github.com/huggingface/transformers/issues/27132
 # please use the slow tokenizer since fast and slow tokenizer produces different tokens
 tokenizer = transformers.AutoTokenizer.from_pretrained(
-        "./Orca-2-13b",
+        "microsoft/Orca-2-13b",
         use_fast=False,
     )