Update README.md

README.md

@@ -13,4 +13,4 @@ It is a ByT5 model finetuned on German-->English translation using the WMT NewsC
 To use the model correctly, you must prepend the prompt with "translate X to Y: ", where X and Y are your source and target languages (e.g. German, English).
 
 
-NOTE: The decoder_start_token_id is 259, which is different from the default token from google/byt5-large (which is 0).
+NOTE: The decoder_start_token_id is 259 for byt5 models and 250099 for mt5 models, which is different from the default token from google's byt5 and mt5 models (which is 0).