|
Help in Finetuning a DistilBert uncased Q/A model
|
|
0
|
275
|
June 2, 2021
|
|
Best way to fine-tune Question-Answer model for different questions
|
|
0
|
538
|
May 29, 2021
|
|
Poor performance in zero-shot learning when using the model 'typeform/distilbert-base-uncased-mnli'
|
|
6
|
2934
|
May 28, 2021
|
|
Yet another question about T5 prefixes: are they special?
|
|
0
|
984
|
May 28, 2021
|
|
Customize pretrained model for model hub
|
|
0
|
377
|
May 27, 2021
|
|
Wav2vec fine-tuning with multiGPU
|
|
16
|
6970
|
May 22, 2021
|
|
GPT Neo 2.7 not working
|
|
2
|
635
|
May 22, 2021
|
|
Is it possible to generate all possible response with model.generate on DialogPT model?
|
|
0
|
253
|
May 21, 2021
|
|
Matching original and translated words with MarianMT
|
|
1
|
1081
|
May 21, 2021
|
|
Data-prep for new portuguese RoBERTa from scratch
|
|
4
|
413
|
May 20, 2021
|
|
Best model for factual/verfiable data?
|
|
1
|
670
|
May 17, 2021
|
|
How to use Bertmodel?
|
|
5
|
1658
|
May 15, 2021
|
|
Is it correct to load weights from task A to train task B
|
|
0
|
322
|
May 6, 2021
|
|
Facing an error in Bert NLP "At most 4 tokens in tensor([ 2, 2, 2, 2, 44763, 44763, 2, 44763]) can be equal to eos_token_id: 2. Make sure tensor([ 2, 2, 2, 2, 44763, 44763, 2, 44763]) are corrected."
|
|
0
|
387
|
May 6, 2021
|
|
Which model is better? sshleifer/distilbart-cnn-12-6 OR sshleifer/distill-pegasus-cnn-16-4
|
|
0
|
334
|
May 5, 2021
|
|
longformer speed compared to bert model
|
|
1
|
1122
|
May 4, 2021
|
|
Long Text generation
|
|
0
|
703
|
May 3, 2021
|
|
Incorrect model ``stas/tiny-wmt19-en-ru``
|
|
1
|
315
|
May 3, 2021
|
|
Batch size, gradient accumulation steps for Linear schedule
|
|
0
|
720
|
May 1, 2021
|
|
Output of BertEmbeddings
|
|
1
|
379
|
May 1, 2021
|
|
Encoder-decoder transformers,
|
|
0
|
327
|
April 30, 2021
|
|
Fine tune Albert, RoBERTa or ELECTRA on SQuAD2.0 and need a model
|
|
0
|
397
|
April 29, 2021
|
|
DialoGPT fine-tuning dataset format
|
|
3
|
727
|
April 27, 2021
|
|
Pre-train PEGASUS model from scratch
|
|
7
|
2839
|
April 25, 2021
|
|
Best summarizer to use for mapping Quora article -> 1 or 2 single sentences
|
|
0
|
383
|
April 22, 2021
|
|
fine tuning encoder decoder for custom language translation
|
|
0
|
478
|
April 22, 2021
|
|
Using RAG with local documents
|
|
3
|
3683
|
April 21, 2021
|
|
Cannot load pretrained tokenizer from 'IlyaGusev/mbart_ru_sum_gazeta' model
|
|
0
|
338
|
April 21, 2021
|
|
MobileBERT decoder returns nans when using fp16 (amp)
|
|
0
|
655
|
April 19, 2021
|
|
```google/pegasus-cnn_dailymail``` generates blank files
|
|
0
|
304
|
April 15, 2021
|