Update README.md

README.md

@@ -9,6 +9,7 @@ datasets:
 This model was trained on slightly adapted code from [run_t5_mlm_flax.py](https://github.com/huggingface/transformers/tree/main/examples/flax/language-modeling). 
 If you want to know about training details or evaluation results, see A. For evaluation, you can also run B.
 
+### How to use
 ```python
 from transformers import T5Tokenizer, T5ForConditionalGeneration