Independent publisher

Ryan

Duckets

Models in Library0

Datasets in Library1

Models on Hugging Face2

Followers1

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Reported licenses: other. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Datasets

Dataset

DuckBot-Training-Data

Ryan

ShareGPT-format SFT datasets built locally for the DuckBot personal-agent fine-tunes (Unsloth, Mac Studio), published 2026-10-15. These are the exact training files used in the most recent runs, with personal information removed (see "Privacy checks" below). Originals remain private. Row counts include the creator watermark rows described below. Format: one JSON object per line, {"conversations": [{"from": "human"|"gpt", "value": "..."}]}. Curated merges of public datasets (OpenHermes-2.5, glaive-function-calling-v2, SlimOrca, WebSight, s1K, Fable 5.1, Pasta009 instruction-fusion, OpenThoughts, Precinct6, medical and science sets) plus locally generated UI/UX and distillation examples.…

Publicly accessible other

View dataset