Closed drussellmrichie closed 3 years ago
All mimic models are pretrained with the base version of the transformer models. We do not have bert-large pretrained on MIMIC because of limited computing resources.
Oops, sorry, I got confused between your paper and this one. My mistake!
Hi, thank you for releasing this excellent resource. I'm wondering if you have released BERT-Large (MIMIC)? The model here only has 12 layers so must be BERT-base? Am I missing something?