canopy-jev: open AI decision model by Ruoxi Qiu

Q: How do I run canopy-jev?

Pull the weights with systemone pull camellia86/canopy-jev and load them with the runtime named in the manifest.

Canopy-Jev-27B

Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.

A rank-16 LoRA on independent copies of the last four text layers plus a ten-letter numerical prior (25 MB of artifacts). The base downloads separately at a pinned revision; it needs the maker's canopy_jev loader, Linux, CUDA and at least 64 GiB of GPU memory. Choice takes 1 to 10 candidates; noul and score are adaptations of that readout. Text only. The maker's own run on JevBench's public items (a third-party benchmark) gives 202/231; the release checkpoint was picked after inspecting several endpoints, so it is not blind, and training used repurposed MMLU and SuperGPQA material. Not calibrated for applications. Weights Apache-2.0, code MIT. Not affiliated with TypeSafe.

What it decides

choice — picks one option from a set
noul — answers a yes/no question with one probability
score — places the input on an ordered scale

At a glance


Parameters	27B
Base model	`Qwen/Qwen3.8-27B`
Maker	Ruoxi Qiu
Released	2026-10-02
License	apache-2.0
Reported accuracy	87.4%

Get the weights

pip install systemonemodels
systemone pull camellia86/canopy-jev

The files are served from the maker's Hugging Face repository, Camellia86/Canopy-Jev-27B, and verified against the checksums recorded here.

Playground

Build a request for camellia86/canopy-jev. 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":"camellia86/canopy-jev","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?"}}}'

Providers

Where this model runs today. Call the provider directly or run the weights yourself.

Provider	Status	Input	Output	Context	Link
Your own hardware	Open weights	Free	Free	—	`systemone pull camellia86/canopy-jev`

Pricing

Availability: Open weights
Licence: apache-2.0
Hosted API: None recorded. Pull the weights and run it yourself.

Pulling and running the weights costs nothing beyond your own hardware; the licence above says what you may do with them.

Performance

Decision accuracy	87.4%

Suite: JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer. Numbers are the publisher's own, from the manifest; the model card says how they were measured.

base_provenance.json1.4 kB
CITATION.cff382 B
CODE_LICENSE.txt1.0 kB
LICENSE11 kB
NOTICE1.1 kB
THIRD_PARTY_NOTICES.md2.4 kB
WEIGHTS_LICENSE.md1.6 kB

adapter.safetensors5026a5324 MB
manifest.json4.6 kB
prior.safetensors686a730200 kB

QWEN_APACHE_2_0.txt11 kB

Every file resolves through a stable path — /v1/models/camellia86/canopy-jev/resolve/0.1.0/<path> — while the object underneath is content-addressed and shared with every other version that holds the same bytes. API reference.

Model tree

Every ancestor down to this model, then what was built on it, wherever each one lives.

Activity

Downloads0

Stars0

Versions1

Built with it0

Latest version: 0.1.0
Updated: Oct 7, 2026
Added to the registry: Oct 7, 2026
Mirrors: camellia86/canopy-jev-27b

Documentation

The HTTP API — every endpoint the website and CLI use.
The CLI — pull this model with systemone pull camellia86/canopy-jev.
systemone.yaml — what the manifest below records.

systemone.yaml

{
  "spec_version": "0.1",
  "model": "canopy-jev",
  "namespace": "camellia86",
  "category": "system-one",
  "architecture": "canopy-jev",
  "base_model": "qwen/qwen3.8-27b",
  "base_model_source": "huggingface",
  "license": "apache-2.0",
  "license_name": null,
  "summary": "Ruoxi Qiu's decision adapter for a frozen Qwen3.8-27B: a 6.3M-parameter LoRA on the last four text layers plus a numerical prior. One shared state feeds isolated question branches; each Choice, Noul or Score question returns probabilities with no generated tokens.",
  "tags": [
    "system-one",
    "qwen",
    "lora",
    "adapter",
    "shared-state",
    "27b"
  ],
  "capabilities": [
    "choice",
    "noul",
    "score"
  ],
  "runtime": {
    "framework": "pytorch",
    "entrypoint": null,
    "python": null,
    "hardware": "gpu"
  },
  "artifacts": [],
  "evaluation": {
    "suite": "JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer",
    "suite_version": null,
    "decision_accuracy": 0.874,
    "calibration_error": null,
    "valid_action_rate": null,
    "median_latency_ms": null,
    "p95_latency_ms": null
  },
  "parameters": 27000000000,
  "context_length": null,
  "hub_repo": "Camellia86/Canopy-Jev-27B",
  "released": "2026-10-02",
  "availability": "open-weights",
  "hosted": null
}

View raw metadata

FAQ

What does canopy-jev decide?

It answers 3 kinds of question: choice picks one option from a list you give it; noul returns the probability that a condition holds; score rates the state on a scale you define. Every answer is a typed value with a probability, never free text.

How do I run canopy-jev?

Pull the weights with systemone pull camellia86/canopy-jev and load them with the runtime named in the manifest.

Can I use canopy-jev commercially?

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

What is canopy-jev built on?

Its base model is qwen/qwen3.8-27b, a canopy-jev architecture. The Model tree section shows the whole chain.

How much can canopy-jev read at once?

The publisher has not recorded a context length. The model has 27B parameters.

How accurate is canopy-jev?

Its publisher reports 87.4% decision accuracy on JevBench public set (231 items; 202 correct), the maker's own fresh zero-shot run with the upstream scorer. Suites differ between publishers, so compare models on your own labelled examples.

How do I link to canopy-jev?

This page is https://systemonemodels.ai/camellia86/canopy-jev. Its metadata is at https://api.systemonemodels.ai/v1/models/camellia86/canopy-jev and a Markdown summary for agents at https://systemonemodels.ai/camellia86/canopy-jev.md.

Ruoxi Qiu: canopy-jev

Canopy-Jev-27B

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ

Ruoxi Qiu: canopy-jev

Canopy-Jev-27B

What it decides

At a glance

Get the weights

Read more

Playground

Providers

Pricing

Performance

Model tree

Activity

Documentation

systemone.yaml

FAQ