How to use Seq2SeqTrainer (Seq2SeqDataCollator) in v4.2.1
|
|
5
|
2566
|
January 20, 2021
|
Distillation: create student model from a different base model than teacher
|
|
9
|
2092
|
October 14, 2020
|
Saving standard BertModel english and BertModel multilingual have drastically different sizes?
|
|
2
|
276
|
August 28, 2020
|
Understanding what went wrong in attention
|
|
5
|
1653
|
July 31, 2020
|
Extremely confusing or non-existent documentation about the Seq2Seq trainer
|
|
1
|
4453
|
December 16, 2021
|
Question regarding TF DistilBert For Sequence Classification
|
|
1
|
271
|
December 16, 2021
|
How to evaluate models
|
|
0
|
2849
|
June 16, 2021
|
Seq-2-Seq Predictions for Longer Sequences and Question for compute metrics function
|
|
0
|
455
|
December 16, 2021
|
Guide: The best way to calculate the perplexity of fixed-length models
|
|
9
|
9470
|
December 16, 2021
|
Using custom csv data with run_summarization.py in sagemaker
|
|
4
|
2071
|
June 16, 2021
|
Getting PermissionError: [WinError 32] When Using Load_Dataset()
|
|
4
|
4373
|
January 19, 2021
|
A hypothetical question on multi-headed wav2vec2 / hubert models
|
|
0
|
346
|
December 15, 2021
|
Can we directly use the embeddings from masked language models?
|
|
0
|
748
|
December 15, 2021
|
PEGASUS extracting from input instead of abstrative summarization
|
|
0
|
270
|
June 16, 2021
|
Github Actions Integration
|
|
1
|
2211
|
December 15, 2021
|
ML for Audio Study Group - Kick Off (Dec 14)
|
|
13
|
2409
|
December 16, 2021
|
Saving-Loading Model in Colab and Making Predictions
|
|
2
|
15346
|
June 15, 2021
|
Xlm-Roberta Tokenizing
|
|
3
|
470
|
January 19, 2021
|
T5: Tips for finetuning on crossword clues (clue => answer)
|
|
1
|
629
|
October 14, 2020
|
Finetune model outputs diffrent predictions at each run ? why?
|
|
0
|
369
|
December 15, 2021
|
New dataset added_review for improvement
|
|
1
|
527
|
December 15, 2021
|
Certain words don't work with bert?
|
|
2
|
312
|
June 15, 2021
|
How do I add features on a local dataset
|
|
2
|
623
|
December 15, 2021
|
How to finetune RAG model with mini batches?
|
|
1
|
417
|
December 15, 2021
|
Pretrained XLM model with TLM objective generates nonsensical predictions
|
|
0
|
533
|
June 15, 2021
|
Distilbart-mnli-12-9
|
|
5
|
545
|
January 19, 2021
|
Partially connected feedforward network
|
|
0
|
195
|
December 15, 2021
|
Precise meaning of ```d_head``` and ```d_inner```
|
|
2
|
1604
|
December 15, 2021
|
Wav2vec2 not converging when finetuning
|
|
7
|
2541
|
June 15, 2021
|
Vector2sequence approach
|
|
0
|
219
|
December 15, 2021
|