Confusion about word vectors and tok2vec

[fcggamou]

Hi, it would be really helpful for me if you would help me understand some underlying concepts about Spacy.

I understand some spacy models have some predefined static vectors, for example, for the Spanish models these are the vectors generated by FastText.
I also understand that there is a tok2vec layer that generates vectors from tokens, and this is used for example as the input of the NER components of the model.

If the above is correct, then I have some questions:

• Does the NER component also use the static vectors?
  - If yes, then where does the tok2vec layer comes into play?
  - If no, then is there any advantage on using the lg or md models if you only intend to use the model for e.g. the NER component?
• Is the tok2vec layer already trained for pretrained downloaded models, e.g. Spanish?
• If I replace the NER component of a pretrained model, does it keep the tok2vec layer untouched i.e. with the learned weights?
• Is the tok2vec layer also trained when I train a NER model?
• Would the pretrain command help the tok2vec layer learn some domain-specific words that may be OOV?

Thanks a lot!

[svlandeg]

I've added some replies to your questions on the related SO post. I'll follow up there, and close this issue to keep the discussion in one place.