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 BSeptember 13, 2019 UTC
.dockerignore
759 BSeptember 13, 2019 UTC
.gitmodules
156 BSeptember 13, 2019 UTC
configurations.yml
4.15 KBSeptember 13, 2019 UTC
CONTRIBUTING.md
1.29 KBSeptember 13, 2019 UTC
Dockerfile
949 BSeptember 13, 2019 UTC
extract_features.py
13.57 KBSeptember 13, 2019 UTC
fp16_utils.py
1.47 KBSeptember 13, 2019 UTC
fused_layer_norm.py
5.49 KBSeptember 13, 2019 UTC
gpu_environment.py
1.53 KBSeptember 13, 2019 UTC
LICENSE
11.09 KBSeptember 13, 2019 UTC
modeling_test.py
8.98 KBSeptember 13, 2019 UTC
modeling.py
37.83 KBSeptember 13, 2019 UTC
multilingual.md
11.03 KBSeptember 13, 2019 UTC
NOTICE
158 BSeptember 13, 2019 UTC
optimization_test.py
1.68 KBSeptember 13, 2019 UTC
optimization.py
17.2 KBSeptember 13, 2019 UTC
predicting_movie_reviews_with_bert_on_tf_hub.ipynbView Notebook
64.93 KBSeptember 13, 2019 UTC
README.md
84.47 KBSeptember 13, 2019 UTC
requirements.txt
110 BSeptember 13, 2019 UTC
run_classifier_with_tfhub.py
11.16 KBSeptember 13, 2019 UTC
run_classifier.py
28.27 KBSeptember 13, 2019 UTC
run.sub
3.11 KBSeptember 13, 2019 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.