|
Train GPT2 from scratch (Tensorflow) - Loss function
|
|
0
|
3
|
March 4, 2021
|
|
Saving memory with run_mlm.py with wikipedia datasets
|
|
0
|
5
|
March 4, 2021
|
|
Example of how to pretrain T5?
|
|
4
|
17
|
March 4, 2021
|
|
Why transformer overfit quickly? how to solve it?
|
|
3
|
494
|
March 4, 2021
|
|
Hyperparameter_search does not log params after first trial
|
|
0
|
7
|
March 4, 2021
|
|
ASR hypotheses rescoring with perplexity score
|
|
0
|
4
|
March 4, 2021
|
|
How to generate a sequence using inputs_embeds instead of input_ids?
|
|
0
|
8
|
March 4, 2021
|
|
How to reduce time at production in T5Tokenizer?
|
|
0
|
10
|
March 4, 2021
|
|
Can I train pytorch T5 on TPU with variable batch shape?
|
|
0
|
11
|
March 3, 2021
|
|
New pipeline for zero-shot text classification
|
|
83
|
10803
|
March 3, 2021
|
|
Bert followed by a GRU
|
|
1
|
16
|
March 3, 2021
|
|
Warning when adding compute_metrics function to Trainer
|
|
9
|
56
|
March 3, 2021
|
|
Uploading files larger than 5GB to model hub
|
|
6
|
21
|
March 3, 2021
|
|
Multilabel sequence classification with Roberta value error expected input batch size to match target batch size
|
|
1
|
191
|
March 2, 2021
|
|
How to get per-eval-step score when using trainer?
|
|
3
|
18
|
March 2, 2021
|
|
How to Improve inference time of facebook/mbart many to many model?
|
|
1
|
18
|
March 2, 2021
|
|
How can I use class_weights when training?
|
|
4
|
218
|
March 1, 2021
|
|
Workflow: how to avoid dummy_pt_objects.py in IDE search results?
|
|
9
|
129
|
February 26, 2021
|
|
Error using `max_length` in transformers
|
|
3
|
28
|
February 26, 2021
|
|
Generation Probabilities: How to compute probabilities of output scores for GPT2
|
|
8
|
221
|
February 26, 2021
|
|
How do we quantize facebook / mbart-large-50-one-to-many-mmt to ONNX runtime
|
|
1
|
23
|
February 26, 2021
|
|
Pytorch BERT model not converging
|
|
1
|
19
|
February 26, 2021
|
|
Multi gpu training
|
|
1
|
27
|
February 25, 2021
|
|
What's the best way to load a saved Tokenizer json into a transformers PreTrainedTokenizerFast (or other transformers tokenizer)?
|
|
3
|
20
|
February 25, 2021
|
|
Trainer gives error after 1st epoch and evaluation
|
|
3
|
18
|
February 25, 2021
|
|
Issue with converting my own BERT TF2 checkpoint to PyTorch and loading the PyTorch model for training
|
|
0
|
12
|
February 25, 2021
|
|
Any reference on how to train (unsupervised learning) longformer model from scratch (not fine-tuning) using Tensorflow?
|
|
0
|
13
|
February 25, 2021
|
|
Different models when loading checkpoint (run_mlm)
|
|
2
|
14
|
February 24, 2021
|
|
BERT for Speech
|
|
1
|
32
|
February 24, 2021
|
|
How to create a tokenizers from a custom pretrained tokenizer?
|
|
1
|
31
|
February 24, 2021
|
