{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:43:34.592Z","data":{"recordId":"wsa_tezbud44v824","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/Phocinae/Phocinae-Largha-150M-v1","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:39:38.860Z","detectedPublishedAt":"2026-10-08T00:30:10.000Z","rights":"original"}],"claims":[{"id":"63ceaf67-0e77-4f5a-bbd8-1e1e288ed5d0","kind":"capability","statement":"The model accepts typed yes/no, choice, and 2–10 score questions and returns answers with confidence in one forward pass.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"**Phocinae-Largha-150M-v1 (Largha) is a 144.3M-parameter bilingual typed decision model — not a chatbot.** Given a `state` plus typed questions (`noul` yes/no · `choice` pick-one · `score` 2–10), it returns calibrated answers with confidence in a single forward pass, emitting…","rights":"original"}}]},{"id":"cb71b3c0-bec9-4bc8-a8da-14d5e24d3ec3","kind":"availability","statement":"Model weights are downloadable from the Phocinae-Largha-150M-v1 Hugging Face repository.","citations":[{"source":1,"supportProbability":0.87,"supports":true,"quote":null}]},{"id":"2e7d8e6c-5b8b-430f-960e-e4e254f2f40d","kind":"deployment","statement":"The official runtime is phocinae-server, and the model can run without a GPU.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"> ⚠️ **This repo is not a chat model, and it does not load through the usual `transformers` path.** Use [phocinae-server](https://github.com/Phocinae/phocinae-server).","rights":"original"}}]},{"id":"04d62342-6fde-44ec-90e9-330df9045a06","kind":"privacy","statement":"The service listens only on 127.0.0.1 and is described as having no telemetry or callbacks.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"dedd6b49-80be-41a2-a742-ee1141488cd4","kind":"capability","statement":"The default runtime rendering path, including phocinae-server 0.1.6, scores 0.5140 on the stated 2,000 decisions; a caller-side override reaches 0.9055.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"c1b375a9-cf5d-47b6-91ce-1e6a3300d700","kind":"recommendation-relevant","statement":"The stated licence for the model is Apache-2.0.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"**It cannot explain itself.** A generative decision model can hand you a one-line reason for a verdict; Largha cannot — that is the trade for determinism and zero output tokens.","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."}}}