NVIDIA
NVIDIA
BERT for TensorFlow
Resource
NVIDIA
NVIDIA
BERT for TensorFlow

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

NameSizeUpdatedActions
__init__.py
616 BMarch 31, 2021 UTC
.dockerignore
779 BMarch 31, 2021 UTC
CONTRIBUTING.md
1.29 KBMarch 31, 2021 UTC
Dockerfile
1.29 KBMarch 31, 2021 UTC
extract_features.py
13.68 KBMarch 31, 2021 UTC
fp16_utils.py
1.47 KBMarch 31, 2021 UTC
fused_layer_norm.py
5.49 KBMarch 31, 2021 UTC
gpu_environment.py
1.53 KBMarch 31, 2021 UTC
LICENSE
11.09 KBMarch 31, 2021 UTC
modeling.py
37.84 KBMarch 31, 2021 UTC
NOTICE
158 BMarch 31, 2021 UTC
README.md
118.32 KBMarch 31, 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.