Update README.md

README.md

@@ -40,7 +40,7 @@ We are providing 2 ways to run the model:
 To load the pretrained model for further finetuning or evaluation:
 ```bash
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("facebook/MobileLLM-125M")
+tokenizer = AutoTokenizer.from_pretrained("facebook/MobileLLM-125M", use_fast_tokenizer=False)
 model = AutoModelForCausalLM.from_pretrained("facebook/MobileLLM-125M", trust_remote_code=True)
 ```
 Note that the default tokenizer does not contain special tokens. For example you can use:
@@ -64,7 +64,7 @@ We provide the pretraining code in https://github.com/facebookresearch/MobileLLM
 # run pretraining
 > bash pretrain.sh 
 ```
-We also provide evaluation script for calculating wiki2 testset ppl
+We also provide evaluation script for calculating ppl of wikitext-2 test split:
 ```bash
 > bash eval.sh
 ```