transformer-model

transformer-model

16 Questions
Newest Active Unanswered Frequent
Score
View
Card Compact
How to understand the self-attention mask implementation in google transformer tutorial
user12692980
•
0
0
11
self-attention transformer-model tensorflow
NLP: transformer learning weights
Jules Santis0
•
0
0
11
self-attention attention-model embedding transformer-model nlp
Why is transformer decoder always generating output of same length as gold labels?
andrea0
•
0
1
22
encoder-decoder huggingface-transformers transformer-model deep-learning nlp
When I run the autoformer model I encounter a ValueError: len() should return >= 0
BigBii0
•
0
0
11
huggingface-transformers transformer-model deep-learning pytorch python
Pytorch for loop vs reshaping "Time Distributed" outputs same forward results, but trains differently
user57IK0
•
0
0
11
transformer-model pytorch nlp python
predicting output symbols in parallel in the seq-to-seq task
MLER0
•
0
0
10
sequence-to-sequence transformer-model parallel-processing
Transformer models seem to be unstable
Masih Bahmani0
•
-2
0
21
transformer-model machine-learning time-series nlp
PyTorch AttributeError: 'NoneType' object has no attribute 'size'
Arianna0
•
0
0
38
class-transformer transformer-model python
AttributeError: 'TFBertModel' object has no attribute 'parameters'
sham Naseer0
•
0
0
21
bert-language-model transformer-model attributeerror nlp python
HuggingFace Summarization: effect of specifying both `do_sample` and `num_beams`
andrea0
•
0
1
30
beam-search summarization huggingface-transformers transformer-model nlp
Hot Questions