AINewsnow

A 26M-parameter tagger beat our fine-tuned small LLMs at grammar correction, and runs in ~4 ms on a phone

This story is from 2026-10-12. It is preserved in the archive; the latest stories are on the live feed.

TL;DR: For grammar correction inside a phone keyboard (on-device only, no network), we compared LoRA fine-tunes of Gemma 3 270M and SmolLM2 360M with a GECToR-style edit tagger we trained from scratch. The 26M tagger (v1.5) wins on accuracy (F0.5 0.799 vs 0.663) and changes correct text 2.4% of the…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-10-12 18:46 · DEV Community — Machine Learning
    A 26M-parameter tagger beat our fine-tuned small LLMs at grammar correction, and runs in ~4 ms on a phone

More stories

  1. Meta releases Muse Wonder models, claiming parity with top AI competitors — Meta Newsroom
  2. Anthropic AI Model Submits False Homicide Tip to Philadelphia Police — The Verge AI
  3. Microsoft president says AI is less regulated than milk — BBC Technology
  4. NVIDIA Opens Vera Rubin Architecture to Scale AI Infrastructure — NVIDIA Blog
  5. Microsoft CEO Nadella calls for AI emergency brake and trust reassessment — CNBC Technology
  6. Microsoft Unveils Maia 300 AI Chip for Multi-Gigawatt Azure Deployments — Techmeme
  7. Epic delays game release to mandate AI-first production — Techmeme
  8. AWS enables global cross-Region inference for OpenAI GPT models on Bedrock — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →