NVIDIA Deep Learning Examples
Transformer-XL for TensorFlow1
Resource
NVIDIA Deep Learning Examples
Transformer-XL for TensorFlow1

Transformer-XL is a transformer-based language model with a segment-level recurrence and a novel relative positional encoding.

  • Changelog

    June 2020

    • upgrade the TensorFlow container to 20.06

    • update performance tables to include A100 results

    • April 2020

      • Initial release
      • Support for FP32 and mixed precision training on NVIDIA DGX-1, NVIDIA DGX-2, and inference on NVIDIA Tesla V100 16G and NVIDIA T4

    Known issues

    There are no known issues with this model.