Update README.md

Author: bdqnghi

README.md

@@ -129,7 +129,7 @@ There are a few notable arguments that need to be considered:
 -  ``model_name``: the name of the model, currently support ``codet5`` and ``causal-lm``. 
 -  ``model_type``: type of model for each model name, e.g. ``base``, ``codegen-350M-mono``, ``j-6B``, etc.
 -  ``load_in_8bit``: inherit the ``load_in_8bit" feature from [Huggingface Quantization](https://huggingface.co/docs/transformers/main/main_classes/quantization).
--  ``weight_sharding``: our advance feature that leverate [HuggingFace Sharded Checkpoint](https://huggingface.co/docs/accelerate/v0.19.0/en/package_reference/big_modeling#accelerate.load_checkpoint_and_dispatch) to split a large model in several smaller shards in different GPUs. Please consider using this if you are dealing with large models.
+-  ``weight_sharding``: our advance feature that leverages [HuggingFace Sharded Checkpoint](https://huggingface.co/docs/accelerate/v0.19.0/en/package_reference/big_modeling#accelerate.load_checkpoint_and_dispatch) to split a large model in several smaller shards in different GPUs. Please consider using this if you are dealing with large models.
 
 ### Model Zoo
 You might want to view all of the supported models. To do this, you can use the ``model_zoo()``: