largha for Ollaya

Ollaya package of Phocinae/Phocinae-Largha-150M-v1 by Phocinae. Ollaya runs open decision models locally, the way Ollama runs LLMs: typed questions in, calibrated answers out, behind a TypeSafe-compatible API.

ollaya run largha

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
largha:150m	Phocinae/Phocinae-Largha-150M-v1@5300e85	150m/model-fp32.onnx, 150m/model-fp16.onnx, 150m/decision.json, 150m/calibration.json

Each tag has an fp32 graph (CPU) and an fp16 graph (GPU). Each tag also has decision.json (sequence layout, special tokens) and calibration.json (temperatures).

Parity

Ollaya's runtime matches laya's own loader (0.3.7, which renders TypeSafe questions as the 0.3.20 Largha was trained with) on the v1.1 checkpoint in fp32: 2,383 questions, identical token ids and markers, the same decision on every question, probabilities within 3.5e-6 on the CPU, CUDA and the Apple GPU (MLX). The fp16 graph agrees on 99.87% of decisions (3 near-ties).

License

Same as the upstream model (Apache-2.0). Ollaya itself is Apache-2.0.