# Institute of Foundation Models: k2-type

> A 0.9B decision model from the Institute of Foundation Models, K2-Horizon-0.9B fully fine-tuned with a pointer head. A state and any number of noul, choice or score questions go in; one forward pass returns a probability per option, with no generated text.

- Page: https://systemonemodels.ai/ifm/k2-type
- API: https://api.systemonemodels.ai/v1/models/ifm/k2-type
- Download: `pip install systemonemodels && systemone pull ifm/k2-type`

## Facts

| | |
|---|---|
| Maker | Institute of Foundation Models (https://systemonemodels.ai/ifm) |
| Decides | choice, score, noul |
| Architecture | k2-horizon |
| Base model | ifm/k2-horizon-0.9b |
| Parameters | 900M |
| Context | 8K tokens |
| Licence | apache-2.0 |
| Availability | Open weights |
| Released | 2026-09-26 |
| Latest version | 2026.09 |

## Reported evaluation

Suite: JevBench public set (231 items), maker's run (jevbench 26eb72d, typesafe adapter). Numbers are the publisher's own.

- Decision accuracy: 76.2%
- Calibration error (ECE): 0.065
- Median latency: 27 ms
- p95 latency: 60 ms

## Model card

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

# K2-Type-0.9B

A 0.9B decision model from the Institute of Foundation Models, K2-Horizon-0.9B fully fine-tuned with a pointer head. A state and any number of noul, choice or score questions go in; one forward pass returns a probability per option, with no generated text.

Choice takes 1 to 255 options and score 2 to 255 levels. A block-causal mask keeps questions independent, and a softmax at a fitted temperature (1.478) gives the probabilities. The repo includes a small server for TypeSafe's /v1/systemone format. 1.08B parameters are stored, including the base model's unused LM head. The maker reports these numbers from its own run of the third-party JevBench public set (231 items): 176 correct (standard 66/72, easy 47/48, hard 63/111), Brier 0.328, ECE 0.065; JevBench's maintainers have queued it but not measured it. Limits the maker states: training code and data are not released; calibration was fitted on Kev's suite, so it may be off on other data; weak at multi-step arithmetic, dates and documents over 8,192 tokens; English only; needs one CUDA GPU and transformers 5.17+ with remote code. First published on 26 Sep as K2-Type-1B and moved into the IFM organisation on 2 Oct.

## 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 | 0.9B |
| Base model | `IFM/K2-Horizon-0.9B` |
| Maker | Institute of Foundation Models |
| Released | 2026-09-26 |
| License | apache-2.0 |
| Reported accuracy | 76.2% |
| Reported latency | 27 ms p50 / 60 ms p95 per decision on one H200, local, about 590 input tokens per decision |

## Get the weights

```bash
pip install systemonemodels
systemone pull ifm/k2-type
```

The files are served from the maker's Hugging Face repository, [`IFM/K2-Type-0.9B`](https://huggingface.co/IFM/K2-Type-0.9B), and verified against the checksums recorded here.

## Read more

- [Model card](https://huggingface.co/IFM/K2-Type-0.9B)
- [Base model K2-Horizon-0.9B](https://huggingface.co/IFM/K2-Horizon-0.9B)

---

*This page was opened by System One for Institute of Foundation Models, 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