|
Marian: Language Discovery questions
|
|
6
|
1570
|
September 15, 2020
|
|
[Proposal] Copy Pasting modeling_bart.py
|
|
4
|
600
|
September 15, 2020
|
|
Saving underlying language model after trained on downstream task
|
|
0
|
420
|
September 14, 2020
|
|
Unstable Reformer training on toy task
|
|
8
|
1116
|
September 14, 2020
|
|
Generating NER data sample for RoBERTa model
|
|
3
|
469
|
September 14, 2020
|
|
What I know and don't know about sequence to sequence batching
|
|
3
|
2027
|
September 11, 2020
|
|
T5 Generates very short summaries
|
|
22
|
5516
|
September 11, 2020
|
|
Merging bert-base-uncased models after trainer but before predict
|
|
6
|
2404
|
September 10, 2020
|
|
T5 weights auto conversion from TF to PyTorch
|
|
1
|
676
|
September 10, 2020
|
|
Issues with translating inputs containing repeated phrases
|
|
1
|
1523
|
September 9, 2020
|
|
NLI 2-sentence classification with GPT2, XLNet, etc.?
|
|
2
|
1937
|
September 9, 2020
|
|
ValueError when trying to use Trainer()
|
|
2
|
783
|
September 8, 2020
|
|
How to get the index of the masked token after passing the sentence to the model
|
|
3
|
2797
|
September 8, 2020
|
|
Good command to test examples/seq2seq refactors
|
|
0
|
237
|
September 3, 2020
|
|
What is the input vector size for a BERT and Transformer-XL?
|
|
1
|
3543
|
September 2, 2020
|
|
Getting import error
|
|
3
|
910
|
September 2, 2020
|
|
S3 uploading advice
|
|
3
|
535
|
August 31, 2020
|
|
Transformers-cli stuck on uploading
|
|
2
|
482
|
August 31, 2020
|
|
Fine tuning reformer model
|
|
0
|
371
|
August 30, 2020
|
|
How much memory is needed for mbart-large-cc25?
|
|
1
|
1079
|
August 29, 2020
|
|
Tricks to control/surpress logging output
|
|
3
|
5486
|
August 29, 2020
|
|
Saving standard BertModel english and BertModel multilingual have drastically different sizes?
|
|
2
|
270
|
August 28, 2020
|
|
Containerizing transformers with Docker and FastAPI
|
|
1
|
2037
|
August 28, 2020
|
|
Gradual Unfreezing support for Fine tuning models
|
|
3
|
3896
|
August 26, 2020
|
|
Training RoBERTa on a large corpus
|
|
5
|
3335
|
August 25, 2020
|
|
Questions about Pegasus for Summarization
|
|
1
|
784
|
August 24, 2020
|
|
Why does the median cross entropy loss change when I change the random seed?
|
|
4
|
703
|
August 23, 2020
|
|
How to evaluate all model ckpts when using `run_language_modeling` with trainer?
|
|
5
|
2182
|
August 21, 2020
|
|
Machine Translation TPU Script
|
|
0
|
266
|
August 20, 2020
|
|
@sgugger Progress Update Aug 4 -> Aug 19
|
|
5
|
392
|
August 20, 2020
|