shipfeedAI news, curated daily

23:04:36 CET
20 MAY23:04:36shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Parcae: Doing more with fewer parameters using stable looped models

Parcae releases a looped language model that matches 1.3B-parameter Transformer quality at 770M parameters, with new scaling laws showing increased recurrence improves compute efficiency.

Apr 15 · · primary fetch1 sourceupdated Apr 15 ·

Parcae is a stable looped language model that matches the quality of a Transformer twice its size — a 770M model reaching 1.3B-level performance.

We introduce the first scaling laws for looping and show that increasing recurrence, not just data, is a compute-efficient path to bet

read full article on together.ai
§ sources1 publication · timeline below
  1. together.aiParcae: Doing more with fewer parameters using stable looped modelsprimary