---
license: apache-2.0
base_model:
- llm-semantic-router/Decision-1.0-Eos-0.8B
library_name: onnx
tags:
- ollaya
- onnx
- decision-model
- system-one
pipeline_tag: text-classification
---

# decision for Ollaya

[Ollaya](https://github.com/ollaya-dev/ollaya) package of **[llm-semantic-router/Decision-1.0-Eos-0.8B](https://huggingface.co/llm-semantic-router/Decision-1.0-Eos-0.8B)** by the vLLM Semantic Router contributors.
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 decision
```

## 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 |
|---|---|---|
| `decision:eos` | [llm-semantic-router/Decision-1.0-Eos-0.8B@3c2d632](https://huggingface.co/llm-semantic-router/Decision-1.0-Eos-0.8B/tree/3c2d632609ceb66f3a13bbc5f77f3ab8cdeebcdd) | `eos/model-fp32.onnx`, `eos/decision.json`, `eos/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 author's code (PyTorch fp32) exactly on 466 questions from 117 requests, and rejects the same 17 requests the author rejects. The token rows and option positions are identical, and so is the decision on every question. Probabilities are within 3.2e-6, on CPU and CUDA, and the TypeSafe answers equal the author's up to 4-decimal rounding.

## License

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