| --- |
| license: other |
| license_name: apache-2.0-and-gemma |
| license_link: https://ai.google.dev/gemma/terms |
| base_model: |
| - hiteshluke/arbiter-4b |
| - unsloth/gemma-3-4b-it |
| library_name: onnx |
| tags: |
| - ollaya |
| - onnx |
| - decision-model |
| - system-one |
| pipeline_tag: text-classification |
| --- |
| |
| # arbiter for Ollaya |
|
|
| [Ollaya](https://github.com/ollaya-dev/ollaya) package of **[hiteshluke/arbiter-4b](https://huggingface.co/hiteshluke/arbiter-4b)** and **[unsloth/gemma-3-4b-it](https://huggingface.co/unsloth/gemma-3-4b-it)** by Codekins Pvt Ltd · Zyot Lab. |
| 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 arbiter |
| ``` |
|
|
| ## What is in this repository |
|
|
| This repository holds only the files Ollaya derives, with no weights. Each graph is an ONNX export of the |
| original model whose weights **reference the authors' own weight files by byte offset**, |
| so `ollaya pull` downloads the weights from the upstream repositories, unmodified and pinned to a |
| commit, and verifies their sha256. |
|
|
| | Tag | Upstream | Files | |
| |---|---|---| |
| | `arbiter:4b` | [hiteshluke/arbiter-4b@0c44271](https://huggingface.co/hiteshluke/arbiter-4b/tree/0c44271c59f89758e3cae17b032e98a9140093e9), [unsloth/gemma-3-4b-it@bf46152](https://huggingface.co/unsloth/gemma-3-4b-it/tree/bf46152c47f5dd20b896357cb51abc4c03b8ee8c) | `4b/model-fp32.onnx`, `4b/decision.json`, `4b/calibration.json` | |
|
|
| Each tag has an fp32 graph, used on CPU and GPU. Each tag also has `decision.json` (sequence layout, special tokens) and |
| `calibration.json` (temperatures). |
|
|
| ## Parity |
|
|
| Ollaya's Rust runtime matches the reference (transformers' Gemma 3 with the authors' LoRA and head, fp32, the training script's prompts) on 420 questions from 127 requests, on CPU and CUDA (RTX 4090): identical token rows, the same 121 rejected requests, the same decision on every question, slot scores within 8.5e-5 and probabilities within 1.0e-5. |
|
|
| ## License |
|
|
| Same as the upstream model (Apache-2.0 (LoRA adapter and head) and the Gemma Terms of Use (Gemma 3 base model)). Ollaya itself is Apache-2.0. |
|
|
