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 BOctober 17, 2019 UTC
.dockerignore
759 BOctober 17, 2019 UTC
.gitmodules
156 BOctober 17, 2019 UTC
configurations.yml
3.94 KBOctober 17, 2019 UTC
CONTRIBUTING.md
1.29 KBOctober 17, 2019 UTC
Dockerfile
949 BOctober 17, 2019 UTC
extract_features.py
13.57 KBOctober 17, 2019 UTC
fp16_utils.py
1.47 KBOctober 17, 2019 UTC
fused_layer_norm.py
5.49 KBOctober 17, 2019 UTC
gpu_environment.py
1.53 KBOctober 17, 2019 UTC
LICENSE
11.09 KBOctober 17, 2019 UTC
modeling_test.py
8.98 KBOctober 17, 2019 UTC
modeling.py
37.84 KBOctober 17, 2019 UTC
multilingual.md
11.03 KBOctober 17, 2019 UTC
NOTICE
158 BOctober 17, 2019 UTC
optimization_test.py
1.68 KBOctober 17, 2019 UTC
optimization.py
16.36 KBOctober 17, 2019 UTC
predicting_movie_reviews_with_bert_on_tf_hub.ipynbView Notebook
64.93 KBOctober 17, 2019 UTC
README.md
93.37 KBOctober 17, 2019 UTC
requirements.txt
110 BOctober 17, 2019 UTC
...