|
SEBIS{URGENT},ValueError: You have to specify either decoder_inputs or decoder_inputs_embeds
|
|
3
|
1203
|
January 1, 2021
|
|
Pre-train PEGASUS model from scratch
|
|
7
|
2824
|
April 25, 2021
|
|
Best summarizer to use for mapping Quora article -> 1 or 2 single sentences
|
|
0
|
381
|
April 22, 2021
|
|
Sentence reordering
|
|
0
|
537
|
December 27, 2020
|
|
TinyReformer/TinyLongformer details
|
|
3
|
432
|
November 6, 2020
|
|
What's the license of joeddav/xlm-roberta-large-xnli?
|
|
3
|
677
|
October 9, 2020
|
|
fine tuning encoder decoder for custom language translation
|
|
0
|
478
|
April 22, 2021
|
|
Using RAG with local documents
|
|
3
|
3663
|
April 21, 2021
|
|
How to evaluate the performance of BERT trained model from scratch?
|
|
0
|
1459
|
December 26, 2020
|
|
Cannot load pretrained tokenizer from 'IlyaGusev/mbart_ru_sum_gazeta' model
|
|
0
|
337
|
April 21, 2021
|
|
MobileBERT decoder returns nans when using fp16 (amp)
|
|
0
|
652
|
April 19, 2021
|
|
Summarization task fails with ProphetNet
|
|
1
|
824
|
December 23, 2020
|
|
Which model to choose for seq2seq(generating headers for articles)?
|
|
0
|
264
|
November 6, 2020
|
|
```google/pegasus-cnn_dailymail``` generates blank files
|
|
0
|
303
|
April 15, 2021
|
|
BART fill-mask and generate summaries
|
|
0
|
321
|
October 11, 2021
|
|
The results of the T5 model for RTE are far from the results as reported in the paper
|
|
0
|
378
|
October 17, 2021
|
|
Finetuning model with smaller sequence size and Dmodel
|
|
0
|
336
|
April 15, 2021
|
|
NER for short technical phrases
|
|
0
|
601
|
December 16, 2020
|
|
OSError: Can't load config for 'MariamD/my-t5-qa-legal'
|
|
0
|
1102
|
October 17, 2021
|
|
How much memory required to load T0pp
|
|
4
|
3703
|
October 20, 2021
|
|
GPT-J weights on HuggingFace
|
|
2
|
385
|
October 20, 2021
|
|
VisionEncoderDecoder/TrOCR
|
|
0
|
702
|
October 21, 2021
|
|
RAG Retriever: hf vs legacy vs exact vs compressed
|
|
8
|
1449
|
October 21, 2021
|
|
New error with gpt-j-6b
|
|
0
|
315
|
October 21, 2021
|
|
Will XLM-R-(X)XL be available in Models?
|
|
1
|
920
|
October 25, 2021
|
|
How to get answer with RobertaForQuestionAnswering
|
|
1
|
1065
|
October 26, 2021
|
|
How to train bilingual models?
|
|
0
|
367
|
October 27, 2021
|
|
Decding Large Audio Files Using Wav2Vec2ForCTC Model
|
|
2
|
740
|
October 28, 2021
|
|
WikiSQL eval scripts for the TAPAS model?
|
|
0
|
383
|
October 29, 2021
|
|
How to push model trained with pytorch_lightning in hugging face?
|
|
0
|
960
|
October 17, 2021
|