# Manjunath Janardhan: opendecider

> Open-weights calibrated decision models by Manjunath Janardhan. The ~400M nano, an Ettin encoder with a decision head, answers typed choice, score and yes/no questions with a probability per option in one forward pass. 4B to 80B LoRA siblings. Apache-2.0.

- Page: https://systemonemodels.ai/manjunath-janardhan/opendecider
- API: https://api.systemonemodels.ai/v1/models/manjunath-janardhan/opendecider
- Download: `pip install systemonemodels && systemone pull manjunath-janardhan/opendecider`

## Facts

| | |
|---|---|
| Maker | Manjunath Janardhan (https://systemonemodels.ai/manjunath-janardhan) |
| Decides | choice, score, noul, classify, route |
| Architecture | opendecider |
| Base model | jhu-clsp/ettin-encoder-400m |
| Parameters | 400M |
| Context | 2K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-27 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: LocalLLaMA/typed-decisions test split (2,000 decisions), the Antz AI Jev-vs-Laya harness; the maker's run, nano fine-tuned on the train split. Numbers are the publisher's own.

- Decision accuracy: 79.6%

- Median latency: 17 ms

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# OpenDecider-nano

Open-weights calibrated decision models by Manjunath Janardhan. The ~400M nano, an Ettin encoder with a decision head, answers typed choice, score and yes/no questions with a probability per option in one forward pass. 4B to 80B LoRA siblings. Apache-2.0.

A personal project. Each option gets its own marker, the logits are softmaxed per question, and all questions run in one batched pass; the answer space is set at request time. Siblings small, small-td (Qwen3-4B-Instruct-2507), medium-td (Qwen3-30B-A3B) and large-td (Qwen3-Next-80B-A3B) are LoRA adapters that read lettered next-token probabilities (Jev-inspired, like Tev1) and need the Qwen base weights. Nano and the -td models were fine-tuned on the typed-decisions train split, so that test score is in-distribution. "Calibrated" is the maker's claim; ECE was measured on 200 general decisions only (nano 0.092), with single training seeds. English only. The opendecider pip package includes a server compatible with Jev's /v1/systemone. The NOTICE lists permissively licensed training data and teacher models.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 400M |
| Base model | `jhu-clsp/ettin-encoder-400m` |
| Maker | Manjunath Janardhan |
| Released | 2026-09-27 |
| License | apache-2.0 |
| Reported accuracy | 79.6% |
| Reported latency | 17 ms per question on an NVIDIA L40S, 18 ms on an Apple M4 Max |

## Get the weights

```bash
pip install systemonemodels
systemone pull manjunath-janardhan/opendecider
```

The files are served from the maker's Hugging Face repository, [`manjunathshiva/opendecider-nano`](https://huggingface.co/manjunathshiva/opendecider-nano), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/manjunathshiva/opendecider-nano)
- [OpenDecider-small-td](https://huggingface.co/manjunathshiva/opendecider-small-td)
- [OpenDecider-large-td](https://huggingface.co/manjunathshiva/opendecider-large-td)
- [Code](https://github.com/manjunathshiva/opendecider)

---

*This page was opened by System One for Manjunath Janardhan, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models