HuggingFace Checkpoint Configurations

[nandovallec]

Hello, I am replicating some of the experiments with the checkpoints from PLBART on HuggingFace.

On the Drive Document (), it is mentioned that the model ('uclanlp/plbart-refine-java-small') does not need a language token. However, if decoder_start_token_id=tokenizer.lang_code_to_id["java"] is not used, the model does not work properly.

Would that be an error in the documentation or am I confusing terms?

Thanks.