MCPcopy Create free account

hub / github.com/circlePi/Pretraining-Yourself-Bert-From-Scratch / functions

Functions114 in github.com/circlePi/Pretraining-Yourself-Bert-From-Scratch

⨍ Functions 114◇ Types & classes 37
Methodget_lr_
(self, progress)
lm_smallBert/pytorch_pretrained_bert/optimization.py:117
Methodget_lr_
(self, progress)
lm_smallBert/pytorch_pretrained_bert/optimization.py:137
Methodget_lr_
(self, progress)
lm_smallBert/pytorch_pretrained_bert/optimization.py:151
Methodget_lr_
(self, progress)
lm_smallBert/pytorch_pretrained_bert/optimization.py:162
Methodinit_bert_weights
Initialize the weights.
lm_smallBert/pytorch_pretrained_bert/modeling.py:512
Functionread_set_from_file
Extract a de-duped collection (set) of text from a file. Expected file format is one item per line.
lm_smallBert/pytorch_pretrained_bert/file_utils.py:255
Functions3_request
Wrapper function for s3 requests in order to create more helpful error messages.
lm_smallBert/pytorch_pretrained_bert/file_utils.py:131
Methodsave_vocabulary
Save the tokenizer vocabulary to a directory or file.
lm_smallBert/pytorch_pretrained_bert/tokenization.py:137
Functionswish
(x)
lm_smallBert/pytorch_pretrained_bert/modeling.py:127
Methodto_json_file
Save this instance to a json file.
lm_smallBert/pytorch_pretrained_bert/modeling.py:222
Methodtokenize
(self, text)
lm_smallBert/pytorch_pretrained_bert/tokenization.py:107
Methodtokenize
Tokenizes a piece of text.
lm_smallBert/pytorch_pretrained_bert/tokenization.py:215
Methodtokenize
Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform tokenization using the gi
lm_smallBert/pytorch_pretrained_bert/tokenization.py:326
Functionwrapper
(url, *args, **kwargs)
lm_smallBert/pytorch_pretrained_bert/file_utils.py:138
← previous101–114 of 114, ranked by callers