Small change; had to rename this to get the Prodigy 101 tutorial to work for NER at https://prodi.gy/docs#first-steps3
In this example, we’re training with 372 total annotations and are using the large [`en_vectors_web_lg` model](https://spacy.io/models/en#en_vectors_web_lg) as the base model. The vectors will be used as features during training, which can give you a nice boost in accuracy. If you don’t have the vector package installed yet, you can download it via `spacy download en_vectors_web_lg` . If you don’t provide an `--eval-id` argument with the name of an evaluation set to evaluate against, Prodigy will hold back a percentage of examples for evaluation, so you can see how your model does on unseen data.