codertimo BERT-pytorch issues

codertimo / BERT-pytorch

Google AI 2018 BERT pytorch implementation

Apache License 2.0

6.08k stars 1.29k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Clarification on Padding Process in BERT Model Construction

#107 AliHaiderAhmad001 opened 7 months ago
0
Why Segment Embedding number only 3?

#106 UTimeStrange opened 7 months ago
1
fix(sec): upgrade torch to 1.13.1

#105 realize096 opened 9 months ago
0
Fix require_grad typo

#104 kit1980 opened 11 months ago
0
请问训练得到的模型后缀为.model.ep*格式，应该如何进行后续的调用呢？

#103 Jwinre opened 1 year ago
0
GELU is available in PyTorch

#102 hubin-keio opened 1 year ago
1
debug BERT-pytorch\bert_pytorch\model\embedding\position.py

#101 wanghesong2019 opened 1 year ago
0
how to fine tune model with trained weight

#100 MingchangLi opened 1 year ago
0
What dataset did you use to train model?

#99 Coding-Child opened 1 year ago
2
why specify `ignore_index=0` in the NLLLoss function in BERTTrainer?

#98 Jasmine969 opened 2 years ago
1
Added a Google Colab Notebook that contains all the code in this project.

#97 ginward opened 2 years ago
1
bert-vocab?

#96 nlpCSir opened 2 years ago
1
Pooler layer?

#95 lihaoxin2020 opened 2 years ago
0
It keeps trying to use CUDA despite --with_cuda False option

#94 hanyangii opened 2 years ago
0
dataset / dataset.py have one erro?

#93 ndn-love opened 2 years ago
1
Why not use torch.no_grad when evaluating test data?

#92 EvanZ opened 3 years ago
1
why language_model.py has different vectors

#91 zysNLP opened 3 years ago
1
Minor comment fix

#90 maengsanha closed 3 years ago
0
The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.

#89 guotong1988 opened 3 years ago
0
IndexError

#88 LemonQC opened 3 years ago
6
An error occurred【AttributeError: type object 'BERT' has no attribute 'hidden'】

#87 XueqiangF opened 3 years ago
0
In Next Sentence Prediction task,the original code may choose the same line when you try to use the negative sample

#86 Emir-Liu opened 3 years ago
0
.

#85 ghost closed 3 years ago
0
residual connection and layernorm according to paper

#84 dshwei opened 3 years ago
0
transformer.py 中的forword方法调用的SublayerConnection类。实现残差链接和标准化的实现

#83 dshwei opened 3 years ago
1
how to do Ner

#82 DeShuiYu opened 3 years ago
0
Default model sizes are much smaller than BERT base

#81 bertmaher opened 3 years ago
0
How to implement model once pretrained for masked input sentences?

#80 sfaux opened 3 years ago
0
How to use this bert model to load and finetune ?

#79 dongrixinyu opened 3 years ago
0
embedding/position.py with RuntimeError if d_model is odd

#78 bookong22 opened 4 years ago
2
Update retrain.py

#77 watseob opened 4 years ago
0
How to Output Embedded Sentence Vector?

#76 rhypowang opened 4 years ago
2
If I want to use /u as a placeholder instead of /t, what do I need to do

#75 0GSC0-0 opened 4 years ago
0
How to use BERT model to fine-tune a cloze-style task?

#74 OrchidXu opened 4 years ago
0
Can you share me a trained data?

#73 vcbeaut opened 4 years ago
0
predict next sentence ony? it also can do SQA assignments?

#72 cqray1990 opened 4 years ago
0
Did you have tried to use ipdb to set breakpoint in __get__item__, which is a funtion from BERTDataset

#71 moomooda opened 4 years ago
1
# of parameter is larger than bert base instead im using specs less than bert base

#70 MohamedLotfyElrefai opened 4 years ago
0
Vocab's load_vectors seems to be an old method?

#69 JamesOwers opened 4 years ago
0
How to Output Embedded Word Vector

#68 enze5088 opened 4 years ago
6
ONNX conversion: TransformerBlock problem

#67 jbmaxwell opened 4 years ago
0
Fix Bug in getting random line

#66 Zenglinxiao opened 5 years ago
0
Erroneous Code

#65 LeoLai930603 opened 5 years ago
0
OOM error in cuda while passing large corpus of wikipedia text files ? how to manage big files to train

#64 MohamedLotfyElrefai opened 5 years ago
0
Add: tqdm total

#63 YongWookHa opened 5 years ago
0
Minor comment typo

#62 BoPengGit opened 5 years ago
0
How can I finetune with this project

#61 Gpwner opened 5 years ago
5
self.d_k = d_model // h gives 64 dimension ?

#60 BerenLuthien opened 5 years ago
1
would you provide some sample datasets for demo the pre-training

#59 SeekPoint closed 4 years ago
9
what does \t be used for here

#58 junchen14 closed 5 years ago
1