Hi, I was working on implementing the XLNet language model in Julia. It uses the sentence-piece as the tokenizer.
I need the vocabulary for the tokenizer, which is stored inside spiece.model file.
I did refer to this Issue #121, but it only tells about modification of the model.
Could you tell me, how I should obtain the vocabulary in a .vocab format?
Hi, I was working on implementing the XLNet language model in Julia. It uses the sentence-piece as the tokenizer. I need the vocabulary for the tokenizer, which is stored inside spiece.model file.
I did refer to this Issue #121, but it only tells about modification of the model.
Could you tell me, how I should obtain the vocabulary in a .vocab format?