GLiNER 2.5 Launches with Architecture Upgrade for Long-Context Extraction
huggingface · x · 2026-08-25
Fastino released GLiNER 2.5, the most significant upgrade to the GLiNER architecture to date. The new model achieves higher average F1 scores across 16 benchmarks compared to GLiNER 2, with a notable 24.75-point gain on XNLI. The improvements stem from a new architecture that predicts entity boundaries directly, allowing inference to scale linearly with document length and removing the max-entity-width cap.
GLiNER 2.5 introduces five new capabilities:
- Long-Context Extraction: Process full documents in a single call.
- Unlimited Span Length: Capture entities of any length, including addresses and titles.
- Joint Inference: Extract and classify entities simultaneously.
Related event: GLiNER 2.5 Released with Boundary Prediction for Full-Document Extraction(3 posts)→
More from Models
- Nathan Lambert slams Meta's Muse Open License as 'trash' — natolambert · 2026-10-16
- Google launches Gemini 4 Argon to Ultra and Pro subscribers, touting physics and 3D skills — ShikharMurty · 2026-10-16
- Google gives X users early access to test Argon, not just companies — lyraxana · 2026-10-16
- Grok Voice 3.0 Tops Design Arena Speech Leaderboard, Up 7.4 Points — XFreeze · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16