Import Transformers into Spark NLP 🚀 #5669
Locked
maziyarpanahi
announced in
Announcement
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Import Transformers into Spark NLP
Overview
We have extended support for
HuggingFace
🤗 andTF Hub
exported models since3.1.0
to equivalent Spark NLP 🚀 annotators. Starting this release, you can easily use thesaved_model
feature in HuggingFace within a few lines of codes and import anyBERT
,DistilBERT
,CamemBERT
,RoBERTa
,DeBERTa
,XLM-RoBERTa
,Longformer
,BertForTokenClassification
,DistilBertForTokenClassification
,AlbertForTokenClassification
,RoBertaForTokenClassification
,DeBertaForTokenClassification
,XlmRoBertaForTokenClassification
,XlnetForTokenClassification
,LongformerForTokenClassification
,CamemBertForTokenClassification
,CamemBertForSequenceClassification
,CamemBertForQuestionAnswering
,BertForSequenceClassification
,DistilBertForSequenceClassification
,AlbertForSequenceClassification
,RoBertaForSequenceClassification
,DeBertaForSequenceClassification
,XlmRoBertaForSequenceClassification
,XlnetForSequenceClassification
,LongformerForSequenceClassification
,AlbertForQuestionAnswering
,BertForQuestionAnswering
,DeBertaForQuestionAnswering
,DistilBertForQuestionAnswering
,LongformerForQuestionAnswering
,RoBertaForQuestionAnswering
,XlmRoBertaForQuestionAnswering
,TapasForQuestionAnswering
,Vision Transformers (ViT)
,HubertForCTC
,SwinForImageClassification
, andConvNextForImageClassification
models to Spark NLP. We will work on the remaining annotators and extend this support to the rest with each release 😊Compatibility
Spark NLP: The equivalent annotator in Spark NLP
TF Hub: Models from TF Hub
HuggingFace: Models from HuggingFace
ONNX: Models from HuggingFace in ONNX format
Model Architecture: Which architecture is compatible with that annotator
Flags:
Example Notebooks
HuggingFace, Optimum, PyTorch, and ONNX Runtime to Spark NLP (ONNX)
HuggingFace to Spark NLP (TensorFlow)
TF Hub to Spark NLP
Beta Was this translation helpful? Give feedback.
All reactions