GLiNER2.5-Decide launches: 340M classifier beats LLM routers on multi-task decisions
philipvollet · x · 2026-09-25
fastino has released GLiNER2.5-Decide, a 340M-parameter English encoder tuned for operational decision tasks.
- Any label set at call time: intent, routing, priority, sentiment, and multi-label tagging in a single forward pass — no prompt templates, no generated tokens; it can also return character-level spans, relations, and structured records.
- Benchmark: on fastino/fast-decisions (17 domains, 300 held-out examples each), it averages 60.2% exact-match accuracy, beating its own 1B variant (59.6%) and rivals like JevK5, SemIf (Qwen3.5-4B), and GLiFormer large-v1.
- A 287M multilingual variant, GLiNER2.5-multi-Decide, covers non-English inputs.
- Explicitly not general-purpose: it targets customer/banking intent, ticket routing, moderation, severity, and agent-completion decisions. Weights are Apache-2.0 on Hugging Face, with hosted inference and a fine-tuning API usable inside coding agents.
More from Models
- LFM2.5-2.6B matches Qwen3.5-9B at 3x size, unlocking on-device agents — helloiamleonie · 2026-09-25
- Inside LFM2.5-2.6B's post-training recipe: SFT, RL, multi-domain distillation — helloiamleonie · 2026-09-25
- Liquid AI explains on-device small model design: antidoom training cuts doom loops from ~10% to 1% in LFM2.5 — helloiamleonie · 2026-09-25
- Codex user reports quota bug: scheduled tasks burn 30% of $200 plan overnight — sethlazar · 2026-09-25
- Elon says SpaceXAI will hit #1 in 6 months; Cursor team's defenders push back — RachelVT42 · 2026-09-25
- Claude Opus 5.5 builds a playable Unreal Engine ARPG — minchoi · 2026-09-25