Model Terminal

ELECTRA Base Discriminator

ELECTRA Base Discriminator is a pretrained transformer encoder from Google Research that learns by detecting replaced tokens rather than masking, making pretraining more compute-efficient than BERT while achieving strong benchmark results on NLP tasks such as classification, QA, and sequence labeling. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
Hugging Face
Openness
Modalities
Text
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed