lukovnikov da2d8ca265 fix for negative learning rate with warmup_linear in BertAdam (happens when t_total is specified incorrectly) ...

+ copied BERT optimization warmup functions to OpenAI optimization file + added comments

2019-02-26 17:16:06 +01:00

..

__init__.py

forgot to add regex to requirements :(

2019-02-18 11:54:51 +01:00

__main__.py

adding gpt2

2019-02-17 23:38:51 +01:00

convert_gpt2_checkpoint_to_pytorch.py

adding gpt2

2019-02-17 23:38:51 +01:00

convert_openai_checkpoint_to_pytorch.py

python 2 compatibility

2019-02-06 00:07:46 +01:00

convert_tf_checkpoint_to_pytorch.py

splitting position and tokens embeddings in OpenAI GPT - updating tf imports - tests

2019-01-29 10:31:42 +01:00

convert_transfo_xl_checkpoint_to_pytorch.py

add two transformer xl models

2019-02-07 17:07:03 +01:00

file_utils.py

fix python 2.7 imports

2019-02-11 10:35:36 +01:00

modeling_gpt2.py

finish updating docstrings

2019-02-23 06:31:59 -08:00

modeling_openai.py

fix tests - bump up version

2019-02-17 23:57:23 +01:00

modeling_transfo_xl_utilities.py

update transfo xl example

2019-02-09 16:59:17 +01:00

modeling_transfo_xl.py

fix TransfoXLModel loading

2019-02-13 09:32:46 +01:00

modeling.py

Update activation function docstring

2019-02-16 12:17:52 -08:00

optimization_openai.py

fix for negative learning rate with warmup_linear in BertAdam (happens when t_total is specified incorrectly)

2019-02-26 17:16:06 +01:00

optimization.py

fix for negative learning rate with warmup_linear in BertAdam (happens when t_total is specified incorrectly)

2019-02-26 17:16:06 +01:00

tokenization_gpt2.py

simple

2019-02-18 11:33:54 +01:00

tokenization_openai.py

OpenAI GPT Tokenizer can fallback on using BERT BasicTokenizer

2019-02-13 10:11:00 +01:00

tokenization_transfo_xl.py

typo

2019-02-20 21:11:06 +08:00

tokenization.py

typo

2019-02-20 21:10:07 +08:00