Improve model card

README.md

@@ -21,7 +21,7 @@ From the abstract:
 
 ## Intended uses & limitations
 
-This repository contains the pre-trained model only, so you can use this model for masked span prediction, as shown in the code example below. However, the main use of this model is to fine-tune it for a downstream task of interest, such as:
+This repository contains the pre-trained model only, so you can use this model for (among other tasks) masked span prediction, as shown in the code example below. However, the main use of this model is to fine-tune it for a downstream task of interest, such as:
 * code summarization
 * code generation
 * code translation
@@ -34,7 +34,7 @@ See the [model hub](https://huggingface.co/models?search=salesforce/codet) to lo
 
 ### How to use
 
-Here is how to use this model:
+Here is how to use this model for masked span prediction:
 
 ```python
 from transformers import RobertaTokenizer, T5ForConditionalGeneration
@@ -103,7 +103,7 @@ The CodeT5 model was pretrained on CodeSearchNet [Husain et al., 2019](https://a
 
 ### Preprocessing
 
-This model uses a code-specific BPE (Byte-Pair Encoding) tokenizer. One can prepare text (or code) for the model using RobertaTokenizer, with the files from this repository.
+This model uses a code-specific BPE (Byte-Pair Encoding) tokenizer trained using the [HuggingFace Tokenizers](https://github.com/huggingface/tokenizers) library. One can prepare text (or code) for the model using RobertaTokenizer, with the files from this repository.
 
 ## Evaluation results