madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1
Madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1 is machine learning model.
About madlag/bert-base-uncased-squadv1-x2.01-f89.2-d30-hybrid-rewind-opt-v1
The model was fine-tuned from the HuggingFace BERT base uncased checkpoint on SQuAD1.1, and distilled from the model bert-large-uncased-whole-word-masking-finetuned-squad . The model contains 45.0% of the original weights overall (the embeddings account for a significant part of the model, and they are not pruned by this method). With a simple resizing of the linear matrices it ran 2.01x as fast as BERT-base on the evaluation. The model is case-insensitive: it does not make a difference between English and English. It is case,