|
OOM issues with save_pretrained models
|
|
0
|
1058
|
March 9, 2021
|
|
Parameter groups and GPT2 LayerNorm
|
|
3
|
651
|
March 9, 2021
|
|
OOM run_seq2seq.py from checkpoint
|
|
0
|
190
|
March 8, 2021
|
|
fine-tune Pegasus with xsum using Colab but generation results have no difference
|
|
0
|
993
|
March 8, 2021
|
|
Different doc with BertForPretraining and TFBertForPretraining
|
|
2
|
285
|
March 7, 2021
|
|
Recommended way to perform batch inference for generation
|
|
0
|
2541
|
March 6, 2021
|
|
Cache T5 encoder results within batch when training
|
|
0
|
485
|
March 6, 2021
|
|
Can I train pytorch T5 on TPU with variable batch shape?
|
|
2
|
302
|
March 6, 2021
|
|
Saving memory with run_mlm.py with wikipedia datasets
|
|
0
|
723
|
March 4, 2021
|
|
Hyperparameter_search does not log params after first trial
|
|
0
|
330
|
March 4, 2021
|
|
ASR hypotheses rescoring with perplexity score
|
|
0
|
1209
|
March 4, 2021
|
|
Bert followed by a GRU
|
|
1
|
1196
|
March 3, 2021
|
|
Warning when adding compute_metrics function to Trainer
|
|
9
|
4827
|
March 3, 2021
|
|
Multilabel sequence classification with Roberta value error expected input batch size to match target batch size
|
|
1
|
4242
|
March 2, 2021
|
|
Workflow: how to avoid dummy_pt_objects.py in IDE search results?
|
|
9
|
1947
|
February 26, 2021
|
|
Error using `max_length` in transformers
|
|
3
|
2705
|
February 26, 2021
|
|
Pytorch BERT model not converging
|
|
1
|
1762
|
February 26, 2021
|
|
What's the best way to load a saved Tokenizer json into a transformers PreTrainedTokenizerFast (or other transformers tokenizer)?
|
|
3
|
4868
|
February 25, 2021
|
|
Issue with converting my own BERT TF2 checkpoint to PyTorch and loading the PyTorch model for training
|
|
0
|
539
|
February 25, 2021
|
|
Any reference on how to train (unsupervised learning) longformer model from scratch (not fine-tuning) using Tensorflow?
|
|
0
|
972
|
February 25, 2021
|
|
Different models when loading checkpoint (run_mlm)
|
|
2
|
505
|
February 24, 2021
|
|
BERT for Speech
|
|
1
|
415
|
February 24, 2021
|
|
How to create a tokenizers from a custom pretrained tokenizer?
|
|
1
|
603
|
February 24, 2021
|
|
Transformers-cli - Python SDK
|
|
0
|
349
|
February 23, 2021
|
|
What FineTuning can be done with a available models
|
|
4
|
445
|
February 23, 2021
|
|
How to load a model and make in parallel (T5)
|
|
0
|
399
|
February 22, 2021
|
|
Loss in on_step_end() callback methods
|
|
1
|
651
|
February 19, 2021
|
|
T5 generation compatibility with original code
|
|
0
|
306
|
February 19, 2021
|
|
Error fine-tuning distilled Pegasus with run_seq2seq.py
|
|
2
|
1036
|
February 18, 2021
|
|
Seeking clarification on MPNet fine-tuning objectives
|
|
0
|
319
|
February 17, 2021
|