Disambiguation evidence for Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity via surface form
"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"
Triples (1)
Triples where some other subject referred to this entity
as "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity".
Noam Shazeer
→
coAuthorOf
→
"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"
ⓘ