|
[RFC] Transformers Pipeline v2
|
|
4
|
1852
|
October 14, 2020
|
|
Finetuning Pegasus for summarization task
|
|
3
|
1052
|
October 14, 2020
|
|
Warning occured when trying to load checkpoint to continue training
|
|
5
|
2273
|
October 13, 2020
|
|
Longformer for sequenceclassification
|
|
5
|
478
|
October 13, 2020
|
|
Using LongformerForMultipleChoice for processing multiple-choice questions with the 4 options
|
|
1
|
664
|
October 13, 2020
|
|
Pplm runtime error with finetuned model
|
|
1
|
558
|
October 12, 2020
|
|
T5 fine tuning, loss difference when using labels and decoder_input_ids
|
|
2
|
1186
|
October 12, 2020
|
|
Strange error when using the Longformer (HuggingFace developers, please reply)
|
|
8
|
1802
|
October 12, 2020
|
|
Do I need token_type_ids for BertForSequenceClassification?
|
|
2
|
216
|
October 12, 2020
|
|
How do we insert our own datasets in DPR / RAG retrieval Q&A models?
|
|
1
|
1647
|
October 11, 2020
|
|
How to get cross-attention values of T5?
|
|
2
|
3869
|
October 9, 2020
|
|
Further Pretrain Basic BERT for sequence classification
|
|
4
|
1817
|
October 9, 2020
|
|
SavedModel export for DistilBERT is failing
|
|
9
|
510
|
October 9, 2020
|
|
Looking for tool class to do predictions
|
|
3
|
557
|
October 9, 2020
|
|
Temporal Information
|
|
0
|
303
|
October 8, 2020
|
|
Change default models text-classification text
|
|
2
|
471
|
October 7, 2020
|
|
Performance with new NVIDIA RTX 30 series
|
|
4
|
5980
|
October 7, 2020
|
|
What is default value for number of labels in BertForSequenceClassification?
|
|
3
|
3928
|
October 5, 2020
|
|
Questions on the `BertModelLMHeadModel`
|
|
7
|
6297
|
October 5, 2020
|
|
GPT2 Training from scratch in German
|
|
3
|
2322
|
October 3, 2020
|
|
Is the multiple-choice head for the pre-trained `LongformerForMultipleChoice` model pre-trained as well?
|
|
1
|
347
|
October 2, 2020
|
|
Calculating accuracy during fine-tuning the BERTForMaskedLM
|
|
6
|
2800
|
October 1, 2020
|
|
Does using FP16 help accelerate generation? (HuggingFace BART)
|
|
2
|
5747
|
September 30, 2020
|
|
Probaility of sequence generated in beam search of GPT2
|
|
0
|
597
|
September 29, 2020
|
|
Loading GPT2 model from Zamia Brain
|
|
0
|
303
|
September 29, 2020
|
|
TypeError when loading a BERT model using TFAutoModel
|
|
1
|
980
|
September 28, 2020
|
|
Issue with max_length
|
|
1
|
2470
|
September 27, 2020
|
|
Training ALBERT from scratch with Distributed Training
|
|
0
|
1707
|
September 25, 2020
|
|
[new model] FSMT has been released + 9 models ported
|
|
3
|
1149
|
September 25, 2020
|
|
[EncoderDecoder] Parameter sharing
|
|
1
|
1012
|
September 24, 2020
|