Let's say that I want to include distilbert https://huggingface.co/distilbert-base-uncased from Hugging Face into spaCy 3.0 pipeline. I think that this is possible and I found some code on how to convert this model for spaCy 2.0 but it doesn't work in v3.0. What I really want is to load this model using something like this
nlp = spacy.load('path_to_distilbert')
Is it even possible and could you please provide the exact steps to do that.
You can use spacy-transformers to this end. In spaCy v3, you can train custom pipelines using a config file, where you would define the transformer component using any HF model you like in components.transformer.model.name:
[components.transformer]
factory = "transformer"
max_batch_items = 4096
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v1"
name = "bert-base-cased"
tokenizer_config = {"use_fast": true}
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.doc_spans.v1"
[components.transformer.set_extra_annotations]
@annotation_setters = "spacy-transformers.null_annotation_setter.v1"
You can then train any other component (NER, textcat, ...) on top of this pretrained transformer model, and the transformer weights will be further finetuned, too.
You can read more about this in the docs here: https://spacy.io/usage/embeddings-transformers#transformers-training
It appears that the only transformer that will work out of the box is their roberta-base model. In the docs it mentions being able to connect thousands of Huggingface models but there is no mention of how to add them to a SpaCy pipeline.
In the meantime if you wanted to use the roberta model you can do the following.
# install using spacy transformers
pip install spacy[transformers]
python -m spacy download en_core_web_trf
import spacy
nlp = spacy.load("en_core_web_trf")