ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
BERT+SQuAD TF Finetuning Notebook
Resource
NVIDIA
NVIDIA
BERT+SQuAD TF Finetuning Notebook

NVIDIA's BERT leverages mixed precision arithmetic and Tensor Cores on A100, V100 and T4 GPUs for faster training while maintaining target accuracy. This notebook demonstrates BERT Question Answering Fine-Tuning with Mixed Precision on SQuaD 2.0 Dataset.

Main repository which contains the dockerfile and the notebooks: https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT

BERT+SQuAD TF Finetuning Notebook： https://github.com/NVIDIA/DeepLearningExamples/blob/master/TensorFlow/LanguageModeling/BERT/notebooks/bert_squad_tf_finetuning.ipynb

You can also download the main repository as a zip file and the jupyter notebook from the "File Browser" section.

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.