| --- |
| license: apache-2.0 |
| base_model: |
| - EldanRing/Winnow-12B |
| - EldanRing/Winnow-E4B |
| tags: |
| - ollaya |
| - gguf |
| - llama.cpp |
| - decision-model |
| - system-one |
| pipeline_tag: text-classification |
| --- |
| |
| # winnow for Ollaya |
|
|
| [Ollaya](https://github.com/ollaya-dev/ollaya) package of **[EldanRing/Winnow-12B](https://huggingface.co/EldanRing/Winnow-12B)** and **[EldanRing/Winnow-E4B](https://huggingface.co/EldanRing/Winnow-E4B)** by EldanRing. |
| Ollaya runs open decision models locally, the way Ollama runs LLMs: typed questions in, |
| calibrated answers out, behind a TypeSafe-compatible API. |
|
|
| ```sh |
| ollaya run winnow |
| ``` |
|
|
| ## What is in this repository |
|
|
| This repository holds only the files Ollaya derives, with no weights. The model is the authors' own GGUF |
| file: `ollaya pull` downloads it from their repository, unmodified and pinned to a commit, verifies its |
| sha256, and Ollaya runs it on llama.cpp. |
|
|
| | Tag | The authors' GGUF | Files | |
| |---|---|---| |
| | `winnow:12b` | [EldanRing/Winnow-12B@b6ac22b](https://huggingface.co/EldanRing/Winnow-12B/tree/b6ac22b0d51b69b18200acacb3fbdd98073fffe8) `gguf/Winnow-12B-Q8_0.gguf` | `12b/decision.json`, `12b/calibration.json` | |
| | `winnow:e4b` | [EldanRing/Winnow-E4B@734302f](https://huggingface.co/EldanRing/Winnow-E4B/tree/734302fe5fbfeb3f21a7ece62653c9539be4aaf3) `gguf/Winnow-E4B-Q8_0.gguf` | `e4b/decision.json`, `e4b/calibration.json` | |
| | `winnow:12b-vision` | [EldanRing/Winnow-12B@b6ac22b](https://huggingface.co/EldanRing/Winnow-12B/tree/b6ac22b0d51b69b18200acacb3fbdd98073fffe8) `gguf/Winnow-12B-Q8_0.gguf` + `gguf/mmproj-Winnow-12B.gguf` | `12b-vision/decision.json`, `12b-vision/calibration.json` | |
| | `winnow:e4b-vision` | [EldanRing/Winnow-E4B@734302f](https://huggingface.co/EldanRing/Winnow-E4B/tree/734302fe5fbfeb3f21a7ece62653c9539be4aaf3) `gguf/Winnow-E4B-Q8_0.gguf` + `gguf/mmproj-Winnow-E4B.gguf` | `e4b-vision/decision.json`, `e4b-vision/calibration.json` | |
|
|
| Each tag has `decision.json` (the prompt, the option labels Ollaya reads and llama.cpp's settings) and |
| `calibration.json` (temperatures). A vision tag also pulls the authors' vision projector from the same revision, which reads the images. |
|
|
| ## Parity |
|
|
| Ollaya's runner matches stock llama-server of the pinned build (b11146) on the same GGUF and the same device: 505 text questions per model, every decision the same, option logits within 1.3e-5 and probabilities within 3.0e-6, on CUDA (RTX 4090, Linux and Windows) and, for e4b, the x86-64 CPU. With the vision projector, 65 image questions per model, every decision the same, option logits within 1.2e-5 (RTX 4070, RTX 5090 and the x86-64 CPU). |
|
|
| ## License |
|
|
| Same as the upstream model (Apache-2.0). Ollaya itself is Apache-2.0. |
|
|
