arbiter for Ollaya

Ollaya package of hiteshluke/arbiter-4b and 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.

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, unsloth/gemma-3-4b-it@bf46152	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.