DigestAI news desk

Cut through the AI noise.

Generative AI & Models4 min read

Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU

The model takes text and a schema of typed questions and returns answers with probability distributions, confidence scores, and constraint-feasibility metadata. It is built on a DeBERTa-v3-large encoder, fine-tuned from gliner2-large-v1, and ships under the Apache 2.0 license. The model installs via pip and runs on CPU, GPU, or in air-gapped environments. Fastino also offers hosted inference and…

1 source

Key points

  • Joint decoding enforces cross-answer rules for guardrails and routing

GLiNER2.5-Decide is a non-generative classifier that uses joint decoding to enforce rules across related answers, such as requiring an unsafe verdict when harm is detected. Fastino evaluated the model on its internal Fast Decisions suite of 5,100 test examples across 17 datasets. The model led on 9 of 17 datasets, scoring 75.3% on support intent and 64.3% on banking intent. Average exact-match accuracy was 60.1%. A 1B-parameter variant and a multilingual 287M model are also available.

Model page: GLiNER2.5-Decide →

Full story from MarkTechPost · by Sana HassanOpen source ↗

Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU

MarkTechPost · 25 September 2026

Loading the full article…

This text was published by MarkTechPost and written by Sana Hassan. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
Fastino LabsMarkTechPostGLiNER2.5-Decidegliner2-large-v1GLiNER2.5-Decide-1BGLiNER2.5-multi-DecideDeBERTa-v3-largeSana Hassan

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Generative AI & Models

All →

Related stories