|
Transformers v4.0.0 announcement
|
|
2
|
2256
|
November 12, 2020
|
|
Clarification: finetune.py max target length
|
|
2
|
448
|
November 12, 2020
|
|
Gradient accumulation averages over gradient
|
|
2
|
2070
|
November 12, 2020
|
|
BERT2BERT Notebook for Models without GenerationMixin
|
|
0
|
289
|
November 12, 2020
|
|
Num_beams: Faster Summarization without Distillation
|
|
1
|
591
|
November 12, 2020
|
|
Why does PretrainedConfig.use_cache default to True?
|
|
0
|
502
|
November 11, 2020
|
|
BartForConditionalGeneration "logits" shape is wrong/unexpected
|
|
4
|
930
|
November 11, 2020
|
|
How to evaluate T5 on classification task in case of multiple tasks
|
|
0
|
592
|
November 11, 2020
|
|
Seq2Seq Distillation: train_distilbart_xsum error
|
|
5
|
440
|
November 10, 2020
|
|
Torchscript vector Input
|
|
0
|
281
|
November 8, 2020
|
|
Pre-trained Sandwich transformer model
|
|
0
|
301
|
November 5, 2020
|
|
Best pre-trained transformer question answer model
|
|
0
|
240
|
November 5, 2020
|
|
Is there a pre-trained BERT model with the sequence length 2048?
|
|
2
|
2111
|
November 5, 2020
|
|
T5-base model create spelling mistake is summary
|
|
2
|
766
|
November 5, 2020
|
|
How to analyze ROCstories with `BertForQuestionAnswering`?
|
|
1
|
291
|
November 5, 2020
|
|
Converting pytorch checkpoints to original roberta pytorch checkpoints
|
|
0
|
655
|
November 4, 2020
|
|
Simple Save/Load of tokenizer not working
|
|
2
|
1668
|
November 4, 2020
|
|
Pipeline for sentiment classification
|
|
6
|
2223
|
November 3, 2020
|
|
Training: "'Trainer' object has no attribute 'epoch'"
|
|
0
|
1027
|
November 3, 2020
|
|
Callbacks method `on_train_batch_end` is slow compared to the batch time; but there is no callbacks
|
|
0
|
2467
|
November 3, 2020
|
|
Load Bert model weights to transformers v3 from model trained with transformers v2
|
|
2
|
301
|
November 2, 2020
|
|
How can I run separately the Encoder and Decoder layers?
|
|
1
|
1810
|
November 2, 2020
|
|
The loss value is not decreasing training the Roberta model
|
|
9
|
11756
|
November 2, 2020
|
|
TypeError: only size-1 arrays can be converted to Python scalars
|
|
1
|
1994
|
October 30, 2020
|
|
[Solved] Issue on translating DPR to TFDPR on loading pytorch weights to TF model
|
|
2
|
518
|
October 29, 2020
|
|
Tfmodelforquestionanswering in eval mode
|
|
2
|
333
|
October 29, 2020
|
|
Multiple choice with variable length options
|
|
1
|
799
|
October 29, 2020
|
|
Hang in language modelling script
|
|
0
|
1212
|
October 29, 2020
|
|
[seq2seq] Run distributed eval somewhat faster than run_eval
|
|
0
|
259
|
October 28, 2020
|
|
TransfoXLLMHeadModel - Trying to create tensor with negative dimension -199500
|
|
1
|
3072
|
October 28, 2020
|