Update example with domain tags

Add information about domain tags

README.md

@@ -18,14 +18,16 @@ To force the target language id as the first generated token, pass the `forced_b
 *Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
 
 To install `sentencepiece` run `pip install sentencepiece`
-
+Note: Since the model was trained with domain tags, you should append them to the input as well.
+"wmtdata newsdomain": Use for sentences in the news domain
+"wmtdata otherdomain": Use for sentences in all other domain
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
 model = AutoModelForSeq2SeqLM.from_pretrained("facebook/wmt21-dense-24-wide-en-x")
 tokenizer = AutoTokenizer.from_pretrained("facebook/wmt21-dense-24-wide-en-x")
 
-inputs = tokenizer("One model for many languages.", return_tensors="pt")
+inputs = tokenizer("wmtdata newsdomain One model for many languages.", return_tensors="pt")
 
 # translate English to German
 generated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.get_lang_id("de"))