This is a checkpoint for BioMegatron 345m cased. BioMegatron is Megatron https://arxiv.org/abs/1909.08053 pretrained on cased PubMed https://catalog.data.gov/dataset/pubmed, a biomedical domain dataset, which gives improved results on a range of biomedical downstream tasks. The model has around 345 million paramters. The model is trained with https://github.com/NVIDIA/Megatron-LM.
The model achieves weighted SAcc/MRR/LAcc of 45.12/61.17/51.4 on BioASQ-7b-factoid test set (after finetuned on SQuADv1.1 dataset), macro precision/recall/f1 of 82.46/78.79/80.52 on RE dataset ChemProt.
Please be sure to download the latest version in order to ensure compatibility with the latest NeMo release.
Megatron is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA, which was trained with multinode and using mixed precision. Unlike BERT, the position of the layer normalization and the residual connection in the model architecture (similar to GPT-2 architucture) are swapped, which allowed the models to continue to improve as they were scaled up. This model reaches higher scores compared to BERT on a range of Natural Language Processing (NLP) tasks. BioMegatron has the same network architecture as the Megatron, but is pretrained on a different dataset - PubMed, a large biomedical text corpus, which achieves better performance in biomedical downstream tasks than the original Megatron.
For more information about BioBERT or Megatron visit https://ngc.nvidia.com/catalog/models/nvidia:biobertbaseuncasedfornemo, https://ngc.nvidia.com/catalog/models/nvidia:biobertlargeuncasedfornemo or https://github.com/NVIDIA/Megatron-LM.
Source code and developer guide is available at https://github.com/NVIDIA/NeMo Refer to documentation at https://docs.nvidia.com/deeplearning/nemo/neural-modules-release-notes/index.html
This model checkpoint can be used for finetuning on biomedical question answering datasets, such as named entity recognition(NER), question answering (QA), or relationship extraction (RE).
In the following we show examples for how to finetune BioBERT on different downstream tasks.