# Telepatia: laya-pt-es-typed

> Portuguese and Spanish fine-tune of Convai's multilingual Laya (322M, mmBERT). Answers choice, score and noul questions over a text state in one forward pass, with a temperature-scaled probability per option. Text only; Apache-2.0.

- Page: https://systemonemodels.ai/telepatia/laya-pt-es-typed
- API: https://api.systemonemodels.ai/v1/models/telepatia/laya-pt-es-typed
- Download: `pip install systemonemodels && systemone pull telepatia/laya-pt-es-typed`

## Facts

| | |
|---|---|
| Maker | Telepatia (https://systemonemodels.ai/telepatia) |
| Decides | choice, score, noul |
| Architecture | laya |
| Base model | convaiinnovations/laya-multilingual |
| Parameters | 322M |
| Context | 1K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-22 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: 384 held-out LocalLLaMA/typed-decisions test questions translated to PT/ES, 64 per language and task, seed 42 (Telepatia's benchmark). Numbers are the publisher's own.

- Decision accuracy: 80.7%
- Calibration error (ECE): 0.027
- Median latency: 18.3 ms
- p95 latency: 18.7 ms

## Model card

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

# Laya PT/ES Typed Decisions

Portuguese and Spanish fine-tune of Convai's multilingual Laya (322M, mmBERT). Answers choice, score and noul questions over a text state in one forward pass, with a temperature-scaled probability per option. Text only; Apache-2.0.

A full fine-tune with no LoRA: stage 1 on LocalLLaMA/typed-decisions translated to Portuguese and Spanish, stage 2 on 2,099 hard examples generated from Common Voice and MLS transcripts. Text only. Telepatia's own benchmark is 384 held-out translated typed-decisions questions, on which it scores 0.807 (Brier 0.111, ECE 0.027) against 0.362 for the base. Probabilities are temperature-scaled on the maker's validation set, so refit them on your own domain before using them as risk scores; score is the weakest primitive, and the benchmark covers four synthetic business workflows. Sibling: Hertz-1, which answers questions about Portuguese and Spanish audio through a speech recogniser feeding a frozen Laya checkpoint (a cascade with fixed option counts and mixed component licences), linked below rather than listed.

## 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

## At a glance

| | |
|---|---|
| Parameters | 322M |
| Base model | `convaiinnovations/laya-multilingual` |
| Maker | Telepatia |
| Released | 2026-09-22 |
| License | apache-2.0 |
| Reported accuracy | 80.7% |
| Reported latency | 18.25 ms p50 / 18.69 ms p95, warm, batch size one, on a Modal A100-40GB |

## Get the weights

```bash
pip install systemonemodels
systemone pull telepatia/laya-pt-es-typed
```

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

## Read more

- [Model card](https://huggingface.co/telepatia-ai/laya-pt-es-typed)
- [Hertz-1 (audio cascade)](https://huggingface.co/telepatia-ai/hertz-1)

---

*This page was opened by System One for Telepatia, 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