NVIDIA
NVIDIA
BERT for TensorFlow2
Resource
NVIDIA
NVIDIA
BERT for TensorFlow2

BERT is a method of pre-training language representations which obtains state-of-the-art results on a wide array of NLP tasks.

NameSizeUpdatedActions
.dockerignore
870 BApril 28, 2021 UTC
classifier_data_lib.py
19.1 KBApril 28, 2021 UTC
common_flags.py
3.94 KBApril 28, 2021 UTC
create_finetuning_data.py
6.61 KBApril 28, 2021 UTC
create_pretraining_data.py
22.85 KBApril 28, 2021 UTC
dllogger_class.py
2.6 KBApril 28, 2021 UTC
Dockerfile
1.74 KBApril 28, 2021 UTC
gpu_affinity.py
1.97 KBApril 28, 2021 UTC
input_pipeline.py
8.58 KBApril 28, 2021 UTC
model_saving_utils.py
4.13 KBApril 28, 2021 UTC
README.md
73.03 KBApril 28, 2021 UTC

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.