google-research bigbird issues

google-research / bigbird

Transformers for Longer Sequences

https://arxiv.org/abs/2007.14062

Apache License 2.0

557 stars 101 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Model for genomic sequences

#36 Prachiiitd opened 8 months ago
0
Variable error with the full_bigbird_mask method in the multi head attention class

#35 BetikuOluwatobi opened 8 months ago
0
the versions of all libraries in the deployment environment?

#34 yangmuli78 opened 1 year ago
0
I've added bigbird's attention to my model, but not seeing a decrease in memory

#33 Currie32 opened 2 years ago
5
Any plan to provide chinese pretrain model ?

#32 DSXiangLi opened 2 years ago
0
fix link of modeling.py

#31 hori-ryota closed 2 years ago
2
Are encoder and decoder both implemented with sparse attention? How long is the verified output length for the decoder?

#30 dongxinghua opened 2 years ago
0
Why is BigBird Pegasus/Pegasus Repeating the Same Sentence for Summarization?

#29 Kevin-Patyk opened 2 years ago
1
Export predictions for each example

#28 jtfields opened 2 years ago
3
TFDS Custom Dataset Issue - normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.

#27 jtfields closed 2 years ago
1
Differences between ETC and BigBird-ETC version

#26 lhl2017 opened 2 years ago
0
How is Prior Arts, which can only accept short text input, evaluated on long text datasets.

#25 cmd0714 opened 2 years ago
0
code error in version of tensorflow?

#24 jaekyoungkim opened 2 years ago
0
Update modeling.py

#23 ikarosilva closed 2 years ago
0
Learning rate mentioned in paper vs run_summarization.py

#22 s4sarath opened 2 years ago
0
What's the difference of bigbr_base and bigbr_base_tf2 at the gs://bigbird-transformer/pretrain ?

#21 liuyang148 opened 2 years ago
0
reproduce arxiv classification task

#20 liuyang148 opened 2 years ago
1
How can we finetune the pretrained model using tfrecord files?

#19 gymbeijing closed 2 years ago
1
Why ``last_idx`` set to 1024 even when sequence length goes upto 4096?

#18 Jeevesh8 opened 3 years ago
0
fix link of modeling.py

#17 hori-ryota closed 2 years ago
2
detail about warm start from RoBERTa’s checkpoint.

#16 RyanHuangNLP opened 3 years ago
0
Error in PubMed evaluation using run_summarization.py

#15 Amit-GH opened 3 years ago
3
Error in run_classifier.py for attention_type=simulated_sparse

#14 Amit-GH opened 3 years ago
0
Precision equals Recall in run_classifier.py script run.

#13 Amit-GH opened 3 years ago
1
bug in line-494 of script- run_pretraining.py

#12 thevasudevgupta opened 3 years ago
0
Unconditional assert False in bigbird/core/utils.py

#11 michaelmherrera opened 3 years ago
0
Couldn't able to save and load the model after finetuning

#10 Maria-philna opened 3 years ago
1
Pegasus variables mapping

#9 huseinzol05 opened 3 years ago
1
Is it valid to train on GRCh38.p13 human reference instead of GRCh37 ?

#8 lovelyscientist opened 3 years ago
0
I want to know d.map("preprocess function",... ) processing

#7 hyungrack opened 3 years ago
0
Preprocessing code for the arxiv classification dataset.

#6 sjy1203 opened 3 years ago
1
Would you like to release the code about how to train a bigbird with other language

#5 RyanHuangNLP closed 3 years ago
1
Preprocessing code for TriviaQA dataset

#4 sjy1203 closed 3 years ago
1
Roberta Training

#3 agemagician opened 3 years ago
4
Pre-trained model for genomic sequences

#2 ptynecki opened 3 years ago
9
Question about pre-trained weights

#1 patrickvonplaten closed 3 years ago
3