|
Based on HF documentation, unnaswerable questions from Squad 2.0 don't make it into train/val data
|
|
4
|
969
|
December 3, 2020
|
|
Using Cross-Encoders to calculate similarities among documents
|
|
3
|
3670
|
December 3, 2020
|
|
Datasets for generating longer summaries
|
|
0
|
287
|
December 3, 2020
|
|
Seq2Seq fnetuning wandb issue
|
|
1
|
876
|
December 3, 2020
|
|
Using summarization models for paraphrasing
|
|
0
|
392
|
December 4, 2020
|
|
[Announcement] Model Versioning: Upcoming changes to the model hub
|
|
34
|
14972
|
December 4, 2020
|
|
Loss rise and acc decline
|
|
0
|
318
|
November 25, 2020
|
|
Why new lines aren't generated?
|
|
0
|
474
|
December 4, 2020
|
|
Finetuning Sequence-Pairs (GLUE) with higher sequence lengths seems to fail?
|
|
1
|
613
|
December 4, 2020
|
|
Zero shot learning
|
|
0
|
299
|
December 4, 2020
|
|
Productionalize the model
|
|
0
|
350
|
December 4, 2020
|
|
Training generative models based on "rewards"
|
|
0
|
288
|
December 4, 2020
|
|
BORT: Optimal Subarchitecture Extraction for BERT
|
|
1
|
539
|
December 5, 2020
|
|
BertTraining Procedure with Pooling Layer
|
|
0
|
309
|
December 5, 2020
|
|
How to save model with .pt extension
|
|
1
|
1768
|
December 6, 2020
|
|
Fundamental newbie questions
|
|
1
|
1329
|
December 6, 2020
|
|
Data collator for training bart from scratch
|
|
1
|
2561
|
December 6, 2020
|
|
Pipeline example in the doc throws an error (question-answering)
|
|
1
|
713
|
December 6, 2020
|
|
What's the difference between bart-base tokenizer and bart-large tokenizer
|
|
6
|
2014
|
December 6, 2020
|
|
How to find the doc - and especially example code - for previous versions?
|
|
1
|
311
|
December 7, 2020
|
|
Why is there no pooler representation for XLNet or a consistent use of sequence_summary()?
|
|
16
|
2180
|
December 7, 2020
|
|
I want to fine tune the KoGPT2 model using Trainer
|
|
0
|
481
|
December 7, 2020
|
|
Couldn't instantiate the backend tokenizer
|
|
0
|
2295
|
December 7, 2020
|
|
Top-k closest/similar words to the input word
|
|
1
|
2183
|
December 7, 2020
|
|
Gradients of BERT layer outputs to inputs
|
|
0
|
1585
|
December 7, 2020
|
|
Sentiment analysis for long sequences
|
|
3
|
2252
|
December 7, 2020
|
|
Advice to speed and performance
|
|
4
|
7189
|
December 7, 2020
|
|
Length_penalty not influencing results (Bart, Pegasus)
|
|
1
|
807
|
December 8, 2020
|
|
Training TransfoXL/GPT2 with fastai gives error
|
|
2
|
333
|
December 8, 2020
|
|
Cross-validation for BERT models
|
|
0
|
976
|
December 8, 2020
|