|
Speeding up T5 inference :rocket:
|
|
10
|
1025
|
January 19, 2021
|
|
Generation Probabilities: How to compute probabilities of output scores for GPT2
|
|
4
|
94
|
January 18, 2021
|
|
LM from Scratch for Tensorflow
|
|
2
|
33
|
January 18, 2021
|
|
XLNetForSequenceClassification
|
|
27
|
144
|
January 16, 2021
|
|
Training models for smaller epochs and then continue trianing
|
|
5
|
45
|
January 16, 2021
|
|
Few shot text generation with T5 transformers like GPT-3
|
|
3
|
81
|
January 15, 2021
|
|
Has anyone here deployed a transformers model on Google Cloud using AI Platform?
|
|
0
|
25
|
January 15, 2021
|
|
Pre-training a language model on a large dataset
|
|
4
|
380
|
January 14, 2021
|
|
Saving check_points for run_mlm.py
|
|
0
|
11
|
January 14, 2021
|
|
[Announcement] GenerationOutputs: Scores, Attentions and Hidden States now available as outputs to generate
|
|
1
|
146
|
January 13, 2021
|
|
T5 fp16 issue is fixed
|
|
1
|
65
|
January 12, 2021
|
|
Problem while uploading a file
|
|
23
|
274
|
January 12, 2021
|
|
Trainer vs seq2seqtrainer
|
|
3
|
43
|
January 12, 2021
|
|
Question About Attention Score Computation & Intuition
|
|
1
|
18
|
January 12, 2021
|
|
Improvements with SWA
|
|
5
|
99
|
January 12, 2021
|
|
Issues running seq2seq distillation
|
|
4
|
58
|
January 11, 2021
|
|
[Blenderbot] Getting runtime error while using generate
|
|
1
|
21
|
January 11, 2021
|
|
Fine-tuning BERT Model on domain specific language and for classification
|
|
4
|
72
|
January 11, 2021
|
|
Seq2Seq-Example does not work on Azure
|
|
2
|
34
|
January 9, 2021
|
|
New pipeline for zero-shot text classification
|
|
77
|
8464
|
January 8, 2021
|
|
`run_glue.py` with my own dataset of one-sentence input
|
|
4
|
56
|
January 8, 2021
|
|
Instantiating TransfoXLTokenizer using existing vocab dict
|
|
1
|
23
|
January 8, 2021
|
|
Rewriting generate function for manual decoder input
|
|
5
|
77
|
January 7, 2021
|
|
Parallelize model call for TFBertModel
|
|
3
|
38
|
January 7, 2021
|
|
`run_qa.py` achieves much lower performance than the original BERT run_squad.py
|
|
2
|
39
|
January 6, 2021
|
|
How to train new token embedding to add to a pretrain model?
|
|
1
|
30
|
January 6, 2021
|
|
Inverse T5 with output (instead of input) prefix
|
|
2
|
33
|
January 6, 2021
|
|
Sentiment Analysis keywords
|
|
3
|
48
|
January 5, 2021
|
|
How can I download my private model?
|
|
4
|
63
|
January 5, 2021
|
|
[Beginner] ClassificationModel Running out of Memory, long training Epochs
|
|
6
|
56
|
January 4, 2021
|
