# Falcons.ai: lightdec

> A 160M-parameter encoder decision model from Falcons.ai on the Ettin-150M backbone. It reads a state of up to 2,048 tokens and answers choice, yes/no (noul) and ordinal score questions in one pass per question, with a temperature-calibrated probability per option.

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

## Facts

| | |
|---|---|
| Maker | Falcons.ai (https://systemonemodels.ai/falcons-ai) |
| Decides | choice, score, noul |
| Architecture | falcondec |
| Base model | jhu-clsp/ettin-encoder-150m |
| Parameters | 160M |
| Context | 2K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-28 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: Falcons.ai FalconDec test split (31,990 items, 73 tasks; falcondec_report.json, the maker's own). Numbers are the publisher's own.

- Decision accuracy: 78.4%
- Calibration error (ECE): 0.029
- Median latency: 10.1 ms
- p95 latency: 10.4 ms

## Model card

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

# LightDec_V2

A 160M-parameter encoder decision model from Falcons.ai on the Ettin-150M backbone. It reads a state of up to 2,048 tokens and answers choice, yes/no (noul) and ordinal score questions in one pass per question, with a temperature-calibrated probability per option.

FalconDec reads the question, every option and the state in one encoder pass; a set-transformer head that ignores option order compares the options, and a temperature per question type and option count calibrates the result, with a defer flag. English only; it needs the falcondec_modeling.py loader in the repo. The maker's numbers come from its own test split, whose tasks are drawn from the same public sources as its training data; on tasks it did not train on accuracy is lower (51.8% on the TEV1 tasks with no source overlap). The card says it is weak at arithmetic, table counting and maths or knowledge tasks, and that prompt-injection detection is not reliable enough to be a sole safety layer; the 100% long-context scores are synthetic. Siblings: LightDec (v1, 512 tokens), LightDec_Arthur (12M byte-level) and Athr_Agent_Sec (an agent-step monitor). The repo also holds Model Surgeon packaging files that are not needed to run the model and are not listed here. Falconsai/laya-v796 is a re-upload of Convai's Laya and is not 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 | 160M |
| Base model | `jhu-clsp/ettin-encoder-150m` |
| Maker | Falcons.ai |
| Released | 2026-09-28 |
| License | apache-2.0 |
| Reported accuracy | 78.4% |
| Reported latency | 10.05 ms p50 per call (one question) on an NVIDIA RTX PRO 6000 Blackwell, fp16; 48.4 ms on CPU with the int8 weights |

## Get the weights

```bash
pip install systemonemodels
systemone pull falcons-ai/lightdec
```

The files are served from the maker's Hugging Face repository, [`Falconsai/LightDec_V2`](https://huggingface.co/Falconsai/LightDec_V2), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/Falconsai/LightDec_V2)
- [LightDec (v1)](https://huggingface.co/Falconsai/LightDec)
- [LightDec_Arthur](https://huggingface.co/Falconsai/LightDec_Arthur)
- [Athr_Agent_Sec](https://huggingface.co/Falconsai/Athr_Agent_Sec)

---

*This page was opened by System One for Falcons.ai, 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