google/electra-small-generator

Fill-Mask • Updated Feb 29, 2024 • 5.21k • • 13

Note Smallest generator model. 12 Layers, 1024 intermediate size, 256 hidden size, 4 attention heads.

google/electra-small-discriminator

Updated Feb 29, 2024 • 114k • 36

Note Smallest discriminator model. 12 Layers, 1024 intermediate size, 256 hidden size, 4 attention heads.

google/electra-base-generator

Fill-Mask • Updated Feb 29, 2024 • 739 • 8

Note Base generator model. 12 Layers, 1024 intermediate size, 256 hidden size, 4 attention heads.

google/electra-base-discriminator

Updated Feb 29, 2024 • 59.8M • 71

Note Base discriminator model. 12 Layers, 3072 intermediate size, 768 hidden size, 12 attention heads.

google/electra-large-generator

Fill-Mask • Updated Feb 29, 2024 • 151 • 8

Note Largest generator model. 24 Layers, 1024 intermediate size, 1024 hidden size, 4 attention heads.

google/electra-large-discriminator

Updated Feb 29, 2024 • 7.24k • 15

Note Largest discriminator model. 24 Layers, 4096 intermediate size, 1024 hidden size, 16 attention heads.