# Eulogik: nirnay

> A 450M decision model from Eulogik: Laya plus a concept bottleneck and a coarse-to-fine pointer, fine-tuned on Banking77 intent. Answers choice, score and yes/no questions with a probability per option in one forward pass. Tuned for banking intent; measure before other uses.

- Page: https://systemonemodels.ai/eulogik/nirnay
- API: https://api.systemonemodels.ai/v1/models/eulogik/nirnay
- Download: `pip install systemonemodels && systemone pull eulogik/nirnay`

## Facts

| | |
|---|---|
| Maker | Eulogik (https://systemonemodels.ai/eulogik) |
| Decides | choice, score, noul, classify |
| Architecture | nirnay |
| Base model | convai-innovations/laya |
| Parameters | 450M |
| Context | 512 tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-30 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Banking77 test split (3,080 items) after fine-tuning on its train split; Eulogik's own eval, raw ECE. Numbers are the publisher's own.

- Decision accuracy: 87.9%
- Calibration error (ECE): 0.089

## Model card

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

# NIRNAY 450M

A 450M decision model from Eulogik: Laya plus a concept bottleneck and a coarse-to-fine pointer, fine-tuned on Banking77 intent. Answers choice, score and yes/no questions with a probability per option in one forward pass. Tuned for banking intent; measure before other uses.

A LoRA on a frozen Laya encoder plus about 30M new parameters, fine-tuned on the Banking77 train split; the maker calls English banking intent, triage and guardrails its only proven lane. On the Banking77 test split Eulogik reports accuracy 0.879, Brier 0.208 and macro-F1 0.879; raw ECE is 0.089, and the card's 0.045 "fitted" figure uses a temperature fitted on the test set itself. Eulogik's own run of the third-party JevBench public set scores 0.550 overall and 0.396 on the hard tier. 512-token context, longer inputs head-truncated. Loads only through the nirnay package from GitHub: phase_b.pt is a PyTorch pickle applied on top of the Laya base weights; an ONNX export is in the repo. The package includes a server with a Jev-compatible /v1/systemone endpoint.

## 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

## At a glance

| | |
|---|---|
| Parameters | 450M |
| Base model | `convai-innovations/laya` |
| Maker | Eulogik |
| Released | 2026-09-30 |
| License | apache-2.0 |
| Reported accuracy | 87.9% |
| Reported latency | 209 ms per decision on an Apple M4 GPU (MPS), 361 ms on CPU, batch 1 |

## Get the weights

```bash
pip install systemonemodels
systemone pull eulogik/nirnay
```

The files are served from the maker's Hugging Face repository, [`eulogik/nirnay-450m`](https://huggingface.co/eulogik/nirnay-450m), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/eulogik/nirnay-450m)
- [Code](https://github.com/eulogik/nirnay)
- [Paper (PDF)](https://github.com/eulogik/nirnay/blob/main/papers/nirnay/main.pdf)

---

*This page was opened by System One for Eulogik, 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