NGC | Catalog
CatalogModelsMegatron-BERT 345M Cased

Megatron-BERT 345M Cased

Logo for Megatron-BERT 345M Cased
345M parameter BERT Megatron model with cased vocab
Latest Version
April 4, 2023
1.25 GB


This is a nemo file for Megatron BERT 345m with cased BERT vocab.

Please be sure to download the latest version in order to ensure compatibility with the latest NeMo release.

Model Architecture

NeMo Megatron is a new capability in the NeMo framework that allows developers to effectively train and scale language models to billions of parameters. 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.

This 345m papameter model has 24 layers (Transformer blocks), 1024 hidden-units, and 16 attention heads.

For more information about NeMo Megatron visit


This model was trained on text sourced from Wikipedia, RealNews, OpenWebText, and CC-Stories. We offer versions of this model pretrained both with a cased and uncased vocabulary.

How to use this Model

NVIDIA NeMo can be used for easy fine-tuning to a number of different tasks. Tutorial notebooks on fine-tuning the model for Named Entity Recognition, Relation Extraction can be found on the tutorials page of NeMo.

Source code and developer guide is available at Refer to documentation at

In the following we show examples for how to finetune BioMegatron on different downstream tasks.

Usage example 1: Finetune on RE dataset ChemProt

Usage example 2: Finetune on NER dataset NBCI


No known limitations available at this time.


License to use this model is covered by the NGC TERMS OF USE unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the NGC TERMS OF USE.