{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:04:49.075Z","data":{"recordId":"wsa_gi33mhazhyx3","score":0.975,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/fastino/GLiNER2.5-multi-Decide","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T01:03:38.885Z","detectedPublishedAt":"2026-09-24T15:32:46.000Z","rights":"original"}],"claims":[{"id":"6c00d7a5-46dd-4ae7-8579-ba98f9b275ac","kind":"capability","statement":"The model accepts label sets at call time for classification.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"**The 287M multilingual classification model in the GLiNER2.5 family.** Pass any label set at call time: intent, routing, sentiment, priority, policy, and multi-label tags, in a single forward pass.","rights":"original"}}]},{"id":"2db79333-0fe3-4d98-a96d-0b8382580586","kind":"capability","statement":"It can score several classification heads in a single forward pass.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"A single call can score several heads at once.","rights":"original"}}]},{"id":"fbf74b5a-145b-4593-94bc-6fb5ae18f4db","kind":"capability","statement":"It is described as a multilingual model for use when input is not English.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"Use [`GLiNER2.5-Decide`](https://huggingface.co/fastino/GLiNER2.5-Decide) for English-only text; use this model when the input is multilingual.","rights":"original"}}]},{"id":"79ea04be-9602-4e20-8620-201e24395d31","kind":"availability","statement":"The model can be loaded with AutoExtractor using fastino/GLiNER2.5-multi-Decide.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":null}]},{"id":"a8dd0dce-adbd-4f54-8a81-df02cf67d785","kind":"recommendation-relevant","statement":"The model is described as a specialist for operational decisions, not a general-purpose model.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"It is a specialist for operational decisions: customer and banking intent, travel and clinic requests, review sentiment, document type, email and ticket routing, human handoff, agent completion, moderation, severity, urgency, and spam.","rights":"original"}}]},{"id":"7143b5d1-3297-4131-9186-89ecb1a626d0","kind":"recommendation-relevant","statement":"It scored 56.7% average exact-match accuracy on the fastino/fast-decisions benchmark.","citations":[{"source":1,"supportProbability":0.95,"supports":true,"quote":{"text":"Exact-match accuracy on [`fastino/fast-decisions`](https://huggingface.co/datasets/fastino/fast-decisions): 17 domains, 300 held-out examples each, with the same text and candidate labels for every model.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}