|
Further train bert with next sentence prediction head using tensorflow
|
|
4
|
1566
|
July 1, 2021
|
|
IndexError: index out of bound, MLM+XLA
|
|
1
|
441
|
June 29, 2021
|
|
How to print a few examples at the beginning of training when using Trainer?
|
|
5
|
2363
|
June 29, 2021
|
|
What happened when Longformer is trained on dataset longer than 4096?
|
|
0
|
297
|
June 29, 2021
|
|
UnicodeDecodeError: xprophetnet-large-wiki100-cased-xglue-qg model
|
|
0
|
347
|
June 28, 2021
|
|
TypeError: forward() got an unexpected keyword argument 'start_positions'
|
|
5
|
6829
|
June 28, 2021
|
|
How to visualize attention of a large encoder-decoder transformer model that isn't a model on hugging face?
|
|
0
|
2334
|
June 28, 2021
|
|
"I am gay." sentence is classified as NEGATIVE with score 0.99
|
|
1
|
521
|
June 28, 2021
|
|
How to train the Translation Language Modeling (TLM) with transformers/examples/language-modeling/run_mlm.py?
|
|
2
|
964
|
June 26, 2021
|
|
Config error for Zero-shot models
|
|
0
|
308
|
June 24, 2021
|
|
Running BigBird on TPUs
|
|
4
|
776
|
June 24, 2021
|
|
[Question] Wav2vec2 word times
|
|
2
|
2974
|
June 24, 2021
|
|
Implementation difference between Bert and Roberta ForSequenceClassification?
|
|
0
|
564
|
June 24, 2021
|
|
Using ResNet50 weights inside `CLIPModel`
|
|
0
|
751
|
June 23, 2021
|
|
BUG Confirmation: BigBirdLM not able to use Flax
|
|
13
|
1275
|
June 23, 2021
|
|
Evaluate model at saved checkpoint
|
|
0
|
1300
|
June 22, 2021
|
|
Eval Loss spike Seq2seq Trainer Resume from Checkpoint
|
|
0
|
522
|
June 22, 2021
|
|
Connection error in transformers
|
|
0
|
1016
|
June 22, 2021
|
|
Do any models support 3 types of token_type_ids?
|
|
0
|
176
|
June 21, 2021
|
|
Speech2Text transformer to ONNX conversion
|
|
0
|
694
|
June 20, 2021
|
|
How to save RoBERTA sequence classifier model
|
|
3
|
2367
|
June 19, 2021
|
|
Modify BERT encoder layers?
|
|
0
|
1026
|
June 18, 2021
|
|
PEGASUS extracting from input instead of abstrative summarization
|
|
0
|
275
|
June 16, 2021
|
|
Wav2vec2 not converging when finetuning
|
|
7
|
2581
|
June 15, 2021
|
|
Wav2Vec model returns zero values
|
|
0
|
491
|
June 12, 2021
|
|
Source attribution with CTRL
|
|
1
|
251
|
June 11, 2021
|
|
How do we quantize facebook / mbart-large-50-one-to-many-mmt to ONNX runtime
|
|
2
|
810
|
June 10, 2021
|
|
gpt-neo-2.7B isn't working with pipleline
|
|
1
|
2318
|
June 10, 2021
|
|
Multi-decoder text generation with BART
|
|
0
|
628
|
June 7, 2021
|
|
How to optimise transformer speed for batches of inputs?
|
|
0
|
260
|
June 7, 2021
|