Ask ten questions, read the text once: making a decision model 6.7x faster

Automated excerpt

Laya is an open model for exactly this job: you send a state (a ticket, an e-mail, a JSON document) and typed questions — choice, score, or a yes/no noul — and a ModernBERT encoder returns calibrated probabilities in one forward pass. Ask ten questions about a 500-token document and the encoder processes the document ten times — about 5,500 tokens for a call whose unique content is about 1,000. every question segment restarts its positions right after [CLS], and the document starts after the longest segment. Switching to the "shared" layout above is what made the accuracy numbers work.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.