namisan/mt-dnn

Issues

• Public access is not permitted

  #257 opened 9 months ago by GCTTTTTT
  2

• ERROR 409: Public access is not permitted on this storage account

  #256 opened a year ago by burry58
  3

• Pretrained weights for transfer learning STS benmark

  #255 opened a year ago by viethoang303
  0

• Problems with downloading datasets and weights

  #252 opened a year ago by Xnhyacinth
  3

• where is run_mt_dnn.sh

  #251 opened a year ago by zhanghanweii
  1

• ddp error in fintune the task-specific like rte

  #254 opened a year ago by Xnhyacinth
  0

• Code for "Targeted Adversarial Training for Natural Language Understanding"

  #250 opened 2 years ago by phkhanhtrinh23
  0

• UnencryptedCookieSessionFactoryConfig

  #213 opened 4 years ago by prince14322
  2

• Older version of Pytorch unavailable

  #248 opened 2 years ago by robfuller7
  1

• Can you provide the pretrain files of Hugging Face?

  #247 opened 2 years ago by chaser-girl
  0

• Readme.md is updated?

  #246 opened 2 years ago by LarissaGuder
  0

• mt-dnn on Windows?

  #245 opened 2 years ago by SimoneGherardi
  0

• question about task split and pretrain model

  #243 opened 2 years ago by chaser-girl
  0

• Project dependencies may have API risk issues

  #242 opened 2 years ago by PyDeps
  0

• Output data in different tasks at the same time

  #237 opened 2 years ago by Szz1897
  0

• RuntimeError with SMART

  #229 opened 3 years ago by xingjianz
  4

• task specific data for fine-tuning

  #221 opened 2 years ago by CarinaXZZ
  1

• Unable to get the complete model MT_DNN

  #235 opened 2 years ago by avyavkumar
  0

• Prediction: How to find the task id?

  #234 opened 3 years ago by hoangthangta
  3

• Performance using ELECTRA and ROBERTA is significantly different from BERT

  #228 opened 3 years ago by chawannut157
  3

• Problem in SMART embedding

  #230 opened 3 years ago by kongds
  1

• I want to know what is the use of argument “local_rank” in training

  #208 opened 3 years ago by XuLongjia
  2

• When using the pre-trained MT-DNN ckpt, the training loss does not converge

  #212 opened 4 years ago by heshenghuan
  4

• Potential bug in predict.py

  #216 opened 3 years ago by chawannut157
  1

• How to convert pytorch_model.bin to .pt so that I can fine tune it with your code?

  #219 opened 3 years ago by junwang4
  1

• support for multi-hop QA

  #202 opened 3 years ago by aliebrahiiimi
  1

• Got problems when preproduce HNN result

  #203 opened 3 years ago by Cy30mk3v
  3

• A issue about score_mask

  #209 opened 3 years ago by sfzhou5678
  1

• Using the model in Colab

  #210 opened 3 years ago by vprelovac
  1

• Projected Gradient Ascent Impleentation

  #224 opened 3 years ago by boubakerwa
  1

• predict.py size mismatch for scoring_list.0.weight and scoring_list.0.bias error

  #227 opened 3 years ago by akkefa
  1

• How we can use mt-dnn to do Multi-Label Classification?

  #226 opened 3 years ago by akkefa
  1

• ImportError: cannot import name 'squad_utils' from 'experiments.squad'

  #225 opened 3 years ago by akkefa
  1

• How to train ny own dataset with MT-DNN

  #215 opened 3 years ago by ammaarahmad1999
  1

• SMART Implementation: SymKLCriterion vs stable_kl

  #222 opened 3 years ago by boubakerwa
  1

• It is difficult to understand Figure 1 in the SMART paper.

  #220 opened 3 years ago by yupeijei1997
  0

• RoBERTa results are much worse than the BERTs'

  #218 opened 3 years ago by DiamondRock
  3

• How to use knowledge distillation on a custom dataset?

  #217 opened 3 years ago by IoSylar
  0

• Posterior Differential Regularization implementation

  #211 opened 3 years ago by shaked571
  1

• An issue about how to make a perturbation in perturbation.py

  #214 opened 4 years ago by TAYAyuki
  0

• ImportError: cannot import name '_truncate_seq_pair' from 'prepro_std'

  #186 opened 4 years ago by huwf9918
  1

• A BUG in preprocess data

  #194 opened 4 years ago by little-black-f
  1

• update mt-dnn/download.sh ?

  #197 opened 4 years ago by leewea
  2

• Maybe it is a bug in mt_dnn/batcher.py

  #187 opened 4 years ago by shiitake8630
  1

• The implement of Mean Teacher for SMART

  #199 opened 4 years ago by YeDeming
  1

• Any instruction in reproducing MC-TACO result?

  #201 opened 4 years ago by PosoSAgapo
  1

• Maybe it is a bug in mt_dnn/model.py

  #196 opened 4 years ago by leewea
  2

• Pre-trained ALUM models?

  #185 opened 4 years ago
  1

• Maybe it is a bug in alum?

  #184 opened 4 years ago by colourful-tree
  3

• Failed to run train.py

  #182 opened 4 years ago by TamHHM
  1