Closed chrisdoyleIE closed 4 years ago
Solution:
The only required arguments concern the .pt itself for fairseq.TransformModel.from_pretrained()
, so the snippet in the issue itself is sufficient, without reference to bpe.
The below snippet is the definition for fairseq.BaseFairseqModel.from_pretrained()
Hi guys,
really incredible work, thank you.
May I please ask for a way of loading the available checkpoints into its fairseq model, such that someone can build upon your architecture?
Specifically, the "bpe" and "bpe_codes" arguments as below are what I'm trying to identify.