Resource
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.
Use the NGC CLI to download:
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
bert_squad_tf_finetuning.ipynbView Notebook | 23.89 KB | May 26, 2021 UTC | |
BERT.zip | 672.79 KB | May 26, 2021 UTC |