Instructions to use ajh-code/Jev-Bonsai-Compass with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajh-code/Jev-Bonsai-Compass with jev-style:

pip install jev-style
# GGUF builds score through llama.cpp: build the jev-score binary once
hf download ajh-code/Jev-Bonsai-Compass build_jev_score.sh jev_score.cpp --local-dir jev-score
export JEV_SCORE_BIN=$(sh jev-score/build_jev_score.sh /path/to/llama.cpp | tail -n 1)

from jev_style import JevStyle, noul, choice

js = JevStyle.from_pretrained("ajh-code/Jev-Bonsai-Compass")
out = js.decide("I was charged twice for one order.", {
    "billing": noul("This message is about billing."),
    "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]),
})
print(out["answers"]["team"]["choice"])

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ajh-code/Jev-Bonsai-Compass with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
./llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ajh-code/Jev-Bonsai-Compass:Q2_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Use Docker

docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0

LM Studio
Jan
Ollama
How to use ajh-code/Jev-Bonsai-Compass with Ollama:
```
ollama run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
```
Unsloth Desktop

How to use ajh-code/Jev-Bonsai-Compass with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ajh-code/Jev-Bonsai-Compass:Q2_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ajh-code/Jev-Bonsai-Compass with Docker Model Runner:
```
docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
```

Lemonade

How to use ajh-code/Jev-Bonsai-Compass with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ajh-code/Jev-Bonsai-Compass:Q2_0

Run and chat with the model

lemonade run user.Jev-Bonsai-Compass-Q2_0

List all available models

lemonade list

Hermes Agent

How to use ajh-code/Jev-Bonsai-Compass with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ajh-code/Jev-Bonsai-Compass:Q2_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ajh-code/Jev-Bonsai-Compass with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ajh-code/Jev-Bonsai-Compass:Q2_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Jev-Bonsai-Compass / README.md

ajh-code

Publish Jev-Bonsai-Compass runtime, adapter, card and evidence

b4b0f75 verified 11 days ago

preview code

Raw History Blame Contribute Delete

4.93 kB

	---
	license: cc-by-nc-4.0
	language:
	- en
	library_name: gguf
	pipeline_tag: text-classification
	base_model: prism-ml/Ternary-Bonsai-2-27B-gguf
	tags:
	- jev
	- jev-style
	- openjev
	- decision-model
	- typed-decisions
	- gguf
	- bonsai
	- ternary
	- local-inference
	- blackwell
	---

	# Jev-Bonsai-Compass

	A complete, local Jev-style text decision download: [Prism's Ternary Bonsai 2 27B](https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf), a decision adapter derived from [OpenJev](https://huggingface.co/openjev/openjev), the tested native server, and a small Python decision API. This is an independent project, not an official Jev or OpenJev release. Fast choices use one short option-scoring pass without reasoning; numerical questions can use a checked CPU calculation.

	## What was measured

	\| Local configuration \| Correct on the same 720 text questions \| Sampled GPU memory \| Mean text-decision latency \|
	\|---\|---:\|---:\|---:\|
	\| Jev-Bonsai-Compass, adapter + compact runtime \| 611/720 (84.9%) \| 7,844 MiB, one RTX 5080 \| 177 ms \|
	\| Full OpenJev FP8 reference \| 615/720 (85.4%) \| 30,974 MiB total, two GPUs \| 118 ms \|
	\| Untuned Bonsai + the same compact runtime \| 584/720 (81.1%) \| 7,510 MiB, one RTX 5080 \| 145 ms \|

	The 720 questions comprise 120 each from AG News, Emotion, BoolQ, SNLI, ARC-Challenge and a 20-intent subset of Banking77. They used identical prompts and option order across the three local configurations. Current versus full OpenJev differs by four answers; a paired bootstrap interval for the accuracy difference is −2.50 to +1.25 percentage points. This does not establish formal parity, and it is not OpenJev's published 10,000-question or hosted Jev evaluation. The full reference used a different two-GPU serving stack, so its latency is not a same-hardware speed comparison. See [domain and method evidence](evidence/core-public-domains.json) and [benchmark metadata](benchmark-manifest.json).

	Accuracy varies by task: this adapter scored 117/120 on science, 113/120 on the selected banking intents, 102/120 on SNLI, and 65/120 on Emotion. It scored 327/328 on reused, authored numerical regressions with compact calculator assistance; that is a system result, not raw-model arithmetic accuracy. [Numeric cases](benchmarks/numeric-regression.jsonl) and [summary evidence](evidence/core-current.json) are included. All timing and memory figures are serial local measurements with context 4,096 and one active request.

	## Download and run

	The complete repository includes one canonical Bonsai GGUF, the adapter, Python source and wheel, a Linux x86-64 native server and shared libraries, examples, licenses, and a [SHA-256 manifest](MANIFEST.json). The bundled native build targets NVIDIA Blackwell `sm_120a` and needs a driver plus CUDA 13, cuBLAS 13 and NCCL 2 system libraries. Python 3.10+ is required; the decision core itself has no third-party Python dependencies.

	```bash
	hf download ajh-code/Jev-Bonsai-Compass --local-dir Jev-Bonsai-Compass
	cd Jev-Bonsai-Compass
	python3 validate_release.py
	bash run.sh serve --gpu 0 --host 127.0.0.1 --port 9304
	```

	In another terminal:

	```bash
	curl -s http://127.0.0.1:9304/v1/decide \
	-H 'Content-Type: application/json' \
	-d '{"state":"There are 9 boxes with 12 pens in each.","question":"How many pens are there?","options":[["a","108"],["b","96"],["c","21"]]}'
	```

	The result contains the selected option ID, method, timing and trace. `bash run.sh decide --input examples/requests.jsonl --gpu 0` processes JSONL without exposing HTTP. `bash run.sh serve --profile base --gpu 0` selects the untuned, Apache-licensed Bonsai path. The server has no authentication; use `--host 127.0.0.1` or a trusted network. For other GPU architectures, build a compatible [Prism llama.cpp fork](https://github.com/PrismML-Eng/llama.cpp) and pass `--binary /path/to/llama-server`.

	## Scope and terms

	The API accepts text `state`, `question`, and 2–26 `[id, description]` options at `POST /v1/decide`; it also provides `/health` and `/v1/capabilities`. It is not a drop-in `/v1/systemone` implementation, vision model, general chat model, or autonomous agent service. Option-relative scores are not guarantees of correctness. The separate experimental agent evidence is included for transparency but its controller is not part of this decision API.

	The bundled adapter contains locally modified OpenJev-derived weight factors and retains CC BY-NC 4.0 noncommercial terms. The unmodified Bonsai base weights are Apache 2.0, this Python software is Apache 2.0, and the native runtime is MIT. The [NOTICE](NOTICE), [licenses](licenses/) and [profile identities](profiles.json) distinguish the components. The adapter is GGUF-formatted data stored as `adapters/broad-lr0.0001.adapter`; `run.sh` loads it directly. The single `.gguf` file is the canonical base model used by both profiles.