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…
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 →
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 ↗
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.
More in Generative AI & Models
All →- Introducing Mistral Large 4 · 7 src
- OpenAI boosts GPT-6 speed by 50% in 28 Days update · 1 src
- Reflection AI debuts Beam, a 501B open-weight model rivaling GLM 5.2 with 3-4x less compute · 10 src
- Author tests four AI assistants on flawed forecasting scenarios · 1 src
- Anthropic prompts users to share voice data to enhance AI models · 8 src
Comments
via GitHub Discussions