What does lev1 decide?

It answers 2 kinds of question: choice picks one option from a list you give it; noul returns the probability that a condition holds. Every answer is a typed value with a probability, never free text.

Pull the weights with systemone pull aviv-dozorets/lev1 and load them with the runtime named in the manifest.

Can I use lev1 commercially?

It is published under apache-2.0. Read the licence before shipping; the model card may add terms of its own.

What is lev1 built on?

Its base model is ifm/k2-horizon-3.7b, a lev1 architecture. The Model tree section shows the whole chain.

How much can lev1 read at once?

The publisher has not recorded a context length. The model has 3.7B parameters.

lev1: open AI decision model by Aviv Dozorets

Lev1-3.7B

A decision model by Aviv Dozorets on IFM's K2-Horizon-3.7B: a rank-32 LoRA, shipped merged and as an adapter, that answers choice and yes/no questions with a probability per option in one forward pass. Not calibrated: raw softmax. Not Interfaze's lev.

Uses custom modeling code copied from IFM, so it needs trust_remote_code. Not calibrated (raw softmax, no fitted temperature). English only; weakest on knowledge and arts. The maker's own run of the third-party Decision Index 0.2.1 gives 42.28 (Tools 68.8), not verified by the board. Unrelated to Interfaze's lev, listed as interfaze-ai/lev.

What it decides

choice — picks one option from a set
noul — answers a yes/no question with one probability

At a glance


Parameters	3.7B
Base model	`IFM/K2-Horizon-3.7B`
Maker	Aviv Dozorets
Released	2026-10-04
License	apache-2.0
Reported latency	28.8 ms p50 / 169.9 ms p95 per request on one RTX PRO 6000 Blackwell Server Edition

Get the weights

pip install systemonemodels
systemone pull aviv-dozorets/lev1

The files are served from the maker's Hugging Face repository, theaviv/Lev1-3.7B, and verified against the checksums recorded here.

Playground

Build a request for aviv-dozorets/lev1. The form and the JSON are the same object; the response panel shows the shape every System One server returns.

Input

StateThe context the questions are asked about. Up to the model's context length.

A yes/no question. The answer is one probability that the condition holds.

Instructions

Response

Placeholder values, in the shape a run returns.

safenoul7%

This model doesn't answer live here. Send this request to your own server for this model; every System One server speaks this shape.

Call it

curl https://api.systemonemodels.ai/v1/systemone \
  -H "Authorization: Bearer $SYSTEMONE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"aviv-dozorets/lev1","state":"Task: clean up inactive accounts before the quarterly report.\nProposed tool call: delete_rows(table=\"customers\", where=\"last_login < 2023-01-01\")\nContext: the customers table is production; there is no backup newer than Friday.","questions":{"safe":{"type":"noul","instructions":"Is this action safe to run without a human approving it first?"}}}'

Median latency	28.8 ms
p95 latency	170 ms

Aviv Dozorets: lev1

Lev1-3.7B

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Aviv Dozorets: lev1

Lev1-3.7B

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ