transformer-model

157 Questions
Newest Active Unanswered Frequent
Score
View
Card Compact
Should the queries, keys and values of the transformer be split before or after being passed through the linear layers?
user_114417310
•
3
0
193
attention-model transformer-model pytorch deep-learning nlp
I get something wrong when use model.train() and model.eval() on pytorch
user_63362880
•
2
0
1084
transformer-model pytorch
How to avoid iterating over Dataloader while resuming training in Huggingface Trainer class?
user_29256220
•
4
1
374
transformer-model huggingface-transformers pytorch
How do I use BertForMaskedLM or BertModel to calculate perplexity of a sentence?
user_108147490
•
9
1
4466
transformer-model bert-language-model huggingface-transformers pytorch nlp
How to finetune distillbart for abstractive summarization using Gigaword or Cnn dailymail?
user_95797190
•
2
0
481
summarization transformer-model bert-language-model huggingface-transformers
How does BertForSequenceClassification classify on the CLS vector?
user_17264040
•
5
1
2051
transformer-model bert-language-model huggingface-transformers python
GPU memory leakage when creating objects from sentence-transformers
user_55594130
•
2
1
1157
transformer-model reticulate pytorch r python-3.x
How to get immediate next word probability using GPT2 model?
user_21812380
•
12
1
3027
transformer-model huggingface-transformers
what the difference between att_mask and key_padding_mask in MultiHeadAttnetion
user_77019080
•
14
2
3937
attention-model transformer-model pytorch deep-learning python
TypeError: Expected any non-tensor type, got a tensor instead
user_99546540
•
5
2
8728
chatbot transformer-model keras tensorflow deep-learning
Hot Questions