MT5 Fine Tuning - KeyError: 'source_ids'
|
|
7
|
1119
|
July 17, 2021
|
Getting NaNs for document relevance model
|
|
0
|
366
|
July 16, 2021
|
[Pytext] Scalable Model Deployment
|
|
1
|
316
|
July 16, 2021
|
Connection error while using tranformers
|
|
0
|
500
|
July 15, 2021
|
Predict beam size on Seq2SeqTrainer
|
|
1
|
278
|
July 15, 2021
|
Good hyperparameter sweeps for text classification model
|
|
0
|
184
|
July 15, 2021
|
Translation - MBART, translation with identical source and target language, for text normalization
|
|
3
|
555
|
July 14, 2021
|
How load a Bert model from Onnx Runtime?
|
|
0
|
2277
|
July 14, 2021
|
How to modify each decoding step in ProphetNet Transformer
|
|
3
|
589
|
July 14, 2021
|
Is there a notebook or document for hyperparameter search?
|
|
2
|
335
|
July 14, 2021
|
ValueError: too many values to unpack (expected 2) when using BertTokenizer
|
|
6
|
8546
|
July 13, 2021
|
Accuracy of MLM model
|
|
5
|
1544
|
July 13, 2021
|
Model doesn't load when using a venv
|
|
1
|
2945
|
July 12, 2021
|
How is T5 pretrained?
|
|
3
|
517
|
July 12, 2021
|
For BERT LMs ... are the random tasks created on just the first sentence or the second as well?
|
|
1
|
251
|
July 11, 2021
|
Has anyone here deployed a transformers model on Google Cloud using AI Platform?
|
|
2
|
1511
|
July 11, 2021
|
T5 for multiple choice
|
|
1
|
429
|
July 10, 2021
|
Custom XLMProphetNetForCG Model, Forward Pass fails
|
|
0
|
196
|
July 10, 2021
|
Is there a way to backpropagate through multiple steps while using Trainer API
|
|
1
|
253
|
July 9, 2021
|
Calling changed functions in transformers/training_args
|
|
1
|
277
|
July 9, 2021
|
ONNX conversion
|
|
0
|
288
|
July 8, 2021
|
TrainingArguments changing the GPU by iteslf
|
|
1
|
355
|
July 7, 2021
|
Can hidden states be passed instead of input_ids or inputs_embeds in Transformers OpenAI GPT2
|
|
0
|
488
|
July 6, 2021
|
Pegasus Questions
|
|
29
|
3953
|
July 5, 2021
|
What is the correct form of decoder_input_ids for LEDForConditionalGeneration?
|
|
1
|
714
|
July 5, 2021
|
How to return entire sentence with AutoModelForQuestionAnswering?
|
|
0
|
281
|
July 4, 2021
|
RoBERTa training low GPU utilization
|
|
6
|
4041
|
July 3, 2021
|
What arguments need to be changed when using deepeed in trainer?
|
|
2
|
471
|
July 3, 2021
|
Trainer API to log both Training and Validation Metrics
|
|
2
|
1690
|
July 1, 2021
|
Finetune language model for feature extraction
|
|
0
|
395
|
July 1, 2021
|