torch.nn.Embedding

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Feb 24 7:59
Editor
Edited
Edited
2024 Mar 1 6:15
Refs
Refs
create token embedding table
  • number of embeddings
  • embedding dimension
  • padding_idx - index of padding token in the input indices
    • The main purpose of this parameter is to provide a way to ignore certain tokens during the embedding lookup, which is particularly useful for batch processing of sequences of varying lengths
    • the embedding vector for the padding index will not be updated during training.
    • This is the token id value not vector index
 
Increasing the vocabulary size to a multiple of 64 means that the data can be more easily divided into equally sized batches that align with the way memory is managed and computations are performed on GPUs.
return embedding tensor for input index tensor
 
 
 
 
 
 

Recommendations