|
`Trainer.predict` takes twice as long as progress bar shows
|
|
1
|
1198
|
June 7, 2021
|
|
Fill mask with subwords
|
|
0
|
352
|
June 6, 2021
|
|
Overfitting in BERT IMDB50k
|
|
0
|
1105
|
June 3, 2021
|
|
Add SENet Blocks in Encoding Layers
|
|
0
|
521
|
June 4, 2021
|
|
Is there a list of MLM corruption strategies?
|
|
1
|
238
|
June 4, 2021
|
|
CUDA error: device-side assert triggered
|
|
3
|
4279
|
June 4, 2021
|
|
LaBSE vs multilingual BERT, same layers?
|
|
1
|
524
|
June 3, 2021
|
|
Does transformers 3.5.1 support auto mixed precision training？
|
|
2
|
454
|
June 1, 2021
|
|
Regression is failing in fine tuning with BERT/GPT-2/Albert
|
|
1
|
1128
|
May 30, 2021
|
|
Does tokenizer.max_model_input_sizes do anything?
|
|
0
|
252
|
May 28, 2021
|
|
Calculating Rouge metric for fine tunning Pegasus
|
|
0
|
1786
|
May 27, 2021
|
|
MaskedLMOutput does not have last_hidden_state
|
|
0
|
1685
|
May 27, 2021
|
|
Wav2Vec2 for Audio Emotion Classification
|
|
6
|
8243
|
May 26, 2021
|
|
Pegasus for text paraphrasing
|
|
0
|
324
|
May 26, 2021
|
|
TensorFlow trainer
|
|
1
|
1010
|
May 26, 2021
|
|
Error when using the forward() function of `LongformerLayer` class
|
|
6
|
1151
|
May 26, 2021
|
|
How can I pretrain a new model re-initializing with my own vocab?
|
|
0
|
296
|
May 25, 2021
|
|
How to train your own corpus without labels
|
|
2
|
3955
|
May 25, 2021
|
|
Difference between LaBSE and BERT multilingual
|
|
0
|
323
|
May 22, 2021
|
|
Approach to get info about word importance
|
|
0
|
476
|
May 22, 2021
|
|
Ask for help with prediction results of Named Entity Recognition Task
|
|
10
|
3238
|
May 21, 2021
|
|
Hyperparameter Tuning QNLI Colab Example using RoBERTa "RuntimeError('CUDA out of memory..."
|
|
0
|
308
|
May 20, 2021
|
|
Architecture attribute of model.config is different from the actual model's architecture in RoBERTa
|
|
1
|
993
|
May 19, 2021
|
|
Pegasus on qa task
|
|
5
|
822
|
May 19, 2021
|
|
Help Improving Abstractive Summarization
|
|
2
|
988
|
May 19, 2021
|
|
Checkpoint missing Optimizer.pt? How to Resume?
|
|
7
|
5526
|
May 18, 2021
|
|
Masked vectors are included in vanilla transformer model
|
|
1
|
539
|
May 17, 2021
|
|
Summarization with mT5
|
|
1
|
1075
|
May 16, 2021
|
|
ELECTRA: Accounting for mask tokens that are correctly predicted by MLM
|
|
9
|
1284
|
May 15, 2021
|
|
Perplexity of BlenderBot
|
|
0
|
432
|
May 13, 2021
|