castorini/hedwig

Issues

• Unable to locate R8 dataset

  #87 opened 2 months ago by LaviRoars
  0

• UnpicklingError with different BERT models

  #83 opened 2 years ago by alpoktem
  0

• BUG report

  #78 opened 3 years ago by NiceMartin
  0

• Paper of HBERT

  #75 opened 4 years ago by KiteFlyKid
  1

• BertForSequenceClassification prediction.

  #23 opened 6 years ago by abhranil08
  2

• [DocBERT] Can DocBERT bin any length document without truncaiton?

  #57 opened 5 years ago by wxp16
  1

• Scaled embedded dropout mask

  #77 opened 4 years ago by plpplp
  1

• labels of the data

  #74 opened 4 years ago by damienlancry
  0

• [Question] What are the "robust" datasets?

  #73 opened 4 years ago by damienlancry
  0

• Getting impossible predicted labels (all zeroes) from custom data

  #72 opened 4 years ago by wailoktam
  0

• Getting AttributeError: Can't get attribute 'gelu' on <module 'transformers.modeling_bert' in "/hedwig/models/bert/__main__.py", l

  #71 opened 4 years ago by wailoktam
  0

• Killed message on trying models.reg_lstm

  #70 opened 4 years ago by bikashg
  1

• does DocBERT freeze all BERT layers and add a fully connected layer on the top for classification?

  #69 opened 4 years ago by vr25
  0

• Custom dataset error

  #68 opened 4 years ago by jmandivarapu1
  4

• Where I can get the KD model

  #67 opened 4 years ago by rafikg
  0

• Bert Inference Issue

  #64 opened 5 years ago by vivekam101
  1

• Fine-tuning BERT for a new dataset

  #63 opened 5 years ago by MarcosFP97
  0

• Alternate hosting for hedwig-data

  #61 opened 5 years ago by achyudh
  8

• DocBERT

  #59 opened 5 years ago by Zhou3983
  3

• Pretrained weights via model zoo

  #56 opened 5 years ago by daemon
  2

• Migrate from pytorch-pretrained-bert to transformers

  #45 opened 5 years ago by achyudh
  1

• Calling BertTokenizer.from_pretrained() with the path to a single file or url is deprecated

  #55 opened 5 years ago by zy1996code
  1

• Reg-LSTM

  #53 opened 5 years ago by daleangus
  1

• fasttext

  #52 opened 5 years ago by daleangus
  1

• DocRoBERTa

  #51 opened 5 years ago by daleangus
  0

• setup

  #50 opened 5 years ago by daleangus
  0

• IMDB dataset

  #49 opened 5 years ago by Mrmoore98
  0

• Memory error with Reuters and models.reg_lstm

  #39 opened 5 years ago by PiercarloSlavazza
  2

• How to feed the document data into DocBert

  #24 opened 6 years ago by xdwang0726
  9

• Early stopping criteria

  #34 opened 5 years ago by fengyunyi
  2

• Correct save location for trained model

  #47 opened 5 years ago by parismic
  1

• fixed-size vector for each large document

  #48 opened 5 years ago by zahra-rou
  2

• Testing a trained model throws error

  #32 opened 5 years ago by Ashutosh-Adhikari
  1

• Replace model caching mechanism

  #9 opened 5 years ago by achyudh
  2

• AttributeError: 'Tensor' object has no attribute 'uniform'

  #40 opened 5 years ago by PiercarloSlavazza
  1

• Number of test and dev lables are not similar to original data

  #35 opened 5 years ago by amirmohammadkz
  0

• Failed saving the best model according to hedwig/models/bert/README.md

  #31 opened 5 years ago by fengyunyi
  6

• Remove tensorboardX logging

  #26 opened 5 years ago by achyudh
  1

• Is there a docker container?

  #22 opened 6 years ago by adrianog
  1

• How do I use this with another dataset?

  #21 opened 6 years ago by adrianog
  1

• self.model.train() should be outside the train-epoch loop

  #18 opened 6 years ago by Ashutosh-Adhikari
  0

• Reproducing Setup and README steps

  #3 opened 6 years ago by gauchm
  3

• DocBERT model weights

  #12 opened 6 years ago by stefan-it
  2

• Add type hints

  #6 opened 6 years ago by daemon
  0

• Use NLTK sent_tokenize and word_tokenize

  #4 opened 6 years ago by achyudh
  0