{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:49:55.074Z","data":{"recordId":"wsa_guk7j9k3f7bu","score":1,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/LiquidAI/d1-Omni-2B","publisher":"Liquid AI","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:20:21.838Z","detectedPublishedAt":"2026-10-24T19:30:58.000Z","rights":"original"},{"n":2,"url":"https://github.com/ollama/ollama/releases/tag/v0.40.12","publisher":"GitHub watchlist","authority":"reputable independent","verification":"verified","lastRetrievedAt":"2026-10-28T00:19:28.612Z","detectedPublishedAt":"2026-10-27T21:41:00.000Z","rights":"original"},{"n":3,"url":"https://huggingface.co/blog/LiquidAI/lfm3","publisher":"Hugging Face","authority":"other","verification":"verified","lastRetrievedAt":"2026-10-28T00:19:24.915Z","detectedPublishedAt":"2026-10-27T17:16:52.000Z","rights":"original"}],"claims":[{"id":"27e72883-d304-4f6c-b04d-6192cc61b212","kind":"capability","statement":"The model returns typed answers with probabilities in a single forward pass and generates no tokens.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":null}]},{"id":"ca8e1082-8b8d-4bc8-9043-93d60489637a","kind":"capability","statement":"Inputs can include text or JSON, pictures, video frames, audio clips, and written or spoken questions.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"<td style=\"border: 0; padding: 0.55em 0.75em;\">A state (text or JSON), pictures, a video, audio clips, and any number of named questions, written or spoken</td>","rights":"original"}}]},{"id":"bc0629c0-5eb4-4773-ab59-b1a1f94074ab","kind":"capability","statement":"It can extract text, numbers, and dates with spans, locate objects in pictures, and estimate quantities with an interval.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- **Beyond classification:** it also extracts text, numbers, and dates with their span, locates objects in pictures, and estimates quantities with an interval.","rights":"original"}}]},{"id":"14e47ab9-fc6c-4782-af5e-ad7593ed4dc4","kind":"availability","statement":"The model checkpoint is available as LiquidAI/d1-Omni-2B on Hugging Face, with Transformers inference instructions.","citations":[{"source":1,"supportProbability":0.86,"supports":true,"quote":null}]},{"id":"c4ca5178-2755-4879-8708-d6865f96e023","kind":"deployment","statement":"The model runs in Transformers with its own model code.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"d1-Omni-2B runs in [Transformers](https://docs.liquid.ai/deployment/gpu-inference/transformers) with its own model code.","rights":"original"}}]},{"id":"94cf2bb7-481b-4d12-a4e1-00d3c0d5dd2e","kind":"recommendation-relevant","statement":"The model is designed for decisions based on audio, including call and voice-message routing and sound events.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"d1-Omni-2B is designed for decisions that depend on what is heard, such as call and voice-message routing and sound events, and it handles the same text and picture decisions as d1-2B.","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."}}}