# Convai Innovations: laya

> An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.

- Page: https://systemonemodels.tech/convai-innovations/laya
- API: https://api.systemonemodels.tech/v1/models/convai-innovations/laya
- Download: `pip install systemonemodels && systemone pull convai-innovations/laya`

## Facts

| | |
|---|---|
| Maker | Convai Innovations (https://systemonemodels.tech/convai-innovations) |
| Decides | choice, score, noul, classify, route |
| Architecture | laya |
| Base model | answerdotai/modernbert-large |
| Parameters | 421M |
| Context | 512 tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-18 |
| Latest version | 2026.09.25 |

## Reported evaluation

Numbers are the publisher's own.

- Median latency: 39.5 ms

## Fine-tunes on the registry

- aac6fef/laya-mlx: https://systemonemodels.tech/aac6fef/laya-mlx

## Model card

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

# Laya

An open-weights System One model from Convai Innovations. A fully fine-tuned ModernBERT-large encoder with a from-scratch decision head that scores one marker per option and answers every question in a single 33–39 ms pass. Runs on your own CPU or GPU.

Laya is trained with Convai's RLCD recipe and proper scoring rules; the base is stated in the README. The repository carries three checkpoints: the English base (421M, 512-token context), a multilingual checkpoint (322M on mmBERT, 1,024 tokens, extendable to 8,192) and a typed-decisions checkpoint. On the typed-decisions suite the base checkpoint scores near chance (36.2%) while the typed-decisions checkpoint scores 76.6%, so pick the checkpoint for the job. Reported calibration error is 0.081 after temperature fitting (0.466 as shipped). laya-serve exposes /v1/systemone; community ports exist for Core ML, MLX, GGUF, ONNX and LiteRT. Fine-tune it on a Mac with Laya Studio.

## 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 calibrated probability
- **classify** — assigns a category from a fixed taxonomy
- **route** — sends the input to one of several destinations

## At a glance

| | |
|---|---|
| Parameters | 421M |
| Base model | `answerdotai/modernbert-large` |
| Maker | Convai Innovations |
| Released | 2026-09-18 |
| License | apache-2.0 |
| Reported latency | 39.5 ms per question on a T4 (English); 32.8 ms multilingual; 193–464 ms on CPU |

## Get the weights

```bash
pip install systemonemodels
systemone pull convai-innovations/laya
```

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

## Read more

- [Source](https://github.com/NandhaKishorM/laya)
- [Weights on Hugging Face](https://huggingface.co/convaiinnovations/laya)
- [Fine-tune with Laya Studio](https://layastudio.biplovgautam.com.np/)

---

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

---

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