google-research/bigbird

Issues

• Model for genomic sequences

  #36 opened a year ago by Prachiiitd
  0

• Variable error with the full_bigbird_mask method in the multi head attention class

  #35 opened a year ago by BetikuOluwatobi
  0

• Pre-trained model for genomic sequences

  #2 opened 4 years ago by ptynecki
  9

• the versions of all libraries in the deployment environment?

  #34 opened 2 years ago by yangmuli78
  0

• reproduce arxiv classification task

  #20 opened 3 years ago by liuyang148
  1

• Why is BigBird Pegasus/Pegasus Repeating the Same Sentence for Summarization?

  #29 opened 3 years ago by Kevin-Patyk
  1

• I've added bigbird's attention to my model, but not seeing a decrease in memory

  #33 opened 3 years ago by Currie32
  5

• Any plan to provide chinese pretrain model ?

  #32 opened 3 years ago by DSXiangLi
  0

• Export predictions for each example

  #28 opened 3 years ago by jtfields
  3

• Are encoder and decoder both implemented with sparse attention? How long is the verified output length for the decoder?

  #30 opened 3 years ago by dongxinghua
  0

• TFDS Custom Dataset Issue - normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.

  #27 opened 3 years ago by jtfields
  1

• Differences between ETC and BigBird-ETC version

  #26 opened 3 years ago by lhl2017
  0

• How is Prior Arts, which can only accept short text input, evaluated on long text datasets.

  #25 opened 3 years ago by cmd0714
  0

• code error in version of tensorflow?

  #24 opened 3 years ago by jaekyoungkim
  0

• Learning rate mentioned in paper vs run_summarization.py

  #22 opened 3 years ago by s4sarath
  0

• What's the difference of bigbr_base and bigbr_base_tf2 at the gs://bigbird-transformer/pretrain ?

  #21 opened 3 years ago by liuyang148
  0

• Error in PubMed evaluation using run_summarization.py

  #15 opened 4 years ago by Amit-GH
  3

• How can we finetune the pretrained model using tfrecord files?

  #19 opened 3 years ago by gymbeijing
  1

• Precision equals Recall in run_classifier.py script run.

  #13 opened 4 years ago by Amit-GH
  1

• Why ``last_idx`` set to 1024 even when sequence length goes upto 4096?

  #18 opened 3 years ago by Jeevesh8
  0

• detail about warm start from RoBERTa’s checkpoint.

  #16 opened 4 years ago by RyanHuangNLP
  0

• Error in run_classifier.py for attention_type=simulated_sparse

  #14 opened 4 years ago by Amit-GH
  0

• Preprocessing code for the arxiv classification dataset.

  #6 opened 4 years ago by sjy1203
  1

• Couldn't able to save and load the model after finetuning

  #10 opened 4 years ago by Maria-philna
  1

• bug in line-494 of script- run_pretraining.py

  #12 opened 4 years ago by thevasudevgupta
  0

• Unconditional assert False in bigbird/core/utils.py

  #11 opened 4 years ago by michaelmherrera
  0

• Pegasus variables mapping

  #9 opened 4 years ago by huseinzol05
  1

• Is it valid to train on GRCh38.p13 human reference instead of GRCh37 ?

  #8 opened 4 years ago by lovelyscientist
  0

• Would you like to release the code about how to train a bigbird with other language

  #5 opened 4 years ago by RyanHuangNLP
  1

• I want to know d.map("preprocess function",... ) processing

  #7 opened 4 years ago by hyungrack
  0

• Preprocessing code for TriviaQA dataset

  #4 opened 4 years ago by sjy1203
  1

• Roberta Training

  #3 opened 4 years ago by agemagician
  4

• Question about pre-trained weights

  #1 opened 4 years ago by patrickvonplaten
  3