Thanks for reaching out to us.
OpenVINO supports the following Bidirectional Encoder Representations from Transformers (BERT) models:
· BERT-Base, Cased
· BERT-Base, Uncased
· BERT-Base, Multilingual Cased
· BERT-Base, Multilingual Uncased
· BERT-Base, Chinese
· BERT-Large, Cased
· BERT-Large, Uncased
Steps for converting BERT models to IR are available here:
We do have the following Intel pre-trained models ;
And also the following public pre-trained model:
IR files are provided for Intel pre-trained models. Meanwhile, the sole public pre-trained model, bert-base-ner, is a PyTorch model, which needs to be converted to ONNX, and subsequently to IR. You can use Model Converter to convert bert-base-ner model into IR format using Model Optimizer.
For your information, the Model Optimizer conversion arguments are given here:
I would suggest you try using similar arguments to convert your .pb file to IR.
For your second question, DistilBert is not yet supported, but we are working on including it in our future releases.
On another note, the ‘small’ Intel pre-trained models are distilled versions as well. For example, ‘bert-small-uncased-whole-word-masking-squad-0001’ is a small BERT-large like model distilled on SQuAD v1.1 training set from the original ‘bert-large-uncased-whole-word-masking-finetuned-squad’ provided by the Transformers library.
Perhaps you can give a try with these pre-trained models to see if they meet your requirements.
This thread will no longer be monitored since we have provided suggestion and explanation. If you need any additional information from Intel, please submit a new question.