---
license: apache-2.0
base_model:
- PostHog/jeeves
library_name: onnx
tags:
- ollaya
- onnx
- decision-model
- system-one
pipeline_tag: text-classification
---

# jeeves for Ollaya

[Ollaya](https://github.com/ollaya-dev/ollaya) package of **[PostHog/jeeves](https://huggingface.co/PostHog/jeeves)** by PostHog (fused weights and pointer head) and the Qwen team (base model).
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 jeeves
```

## 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 |
|---|---|---|
| `jeeves:9b` | [PostHog/jeeves@8622b7d](https://huggingface.co/PostHog/jeeves/tree/8622b7d1652a9dcb8629486b84dce9e8d690c5cd) | `9b/model-fp32.onnx`, `9b/decision.json`, `9b/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 authors' own code (their Qwen3.5 model and pointer head, fp32, no thinking) on 430 questions from 107 requests, on CUDA: identical token rows and option positions, the same 16 rejected requests, the same decision on every question, scores within 1.9e-4 and probabilities within 1.4e-5.

## License

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