MiniCPM5-2B-Jev is an open-source, calibrated System 1 Decision Model built on OpenBMB’s MiniCPM5-2B.

It is specifically trained for fast, structured decision-making tasks such as support ticket triage, content moderation, policy enforcement, and agent decision routing.

1. Quickstart

Pull the Model

ollama pull actbro/minicpm5-2b-jev

Run via Command Line

ollama run actbro/minicpm5-2b-jev "Context: Customer upgraded from Basic to Enterprise and needs SSO SAML configuration.

Question: Which support queue should handle this ticket?
Options:
(A) Billing & Invoices
(B) Enterprise Onboarding (SSO, SAML, dedicated cluster)
(C) General Technical Support
Answer: ("

2. Benchmark Highlights

• #1 on JevBench: Ranks #1 among all ≤ 2B open-weight models with 78.79% accuracy.
• Top Decision Accuracy: Achieves 86.41% accuracy on the 10-source decision-v7 benchmark, outperforming proprietary TypeSafe Hosted Jev (84.50%) and Together AI’s Tev1 4B (73.3%).
• Compact & Fast: Lightweight 2B architecture, runs smoothly and efficiently on consumer hardware and Apple Silicon.

3. Ollama Usage Examples

Python (using Ollama API)

import requests

prompt = """Context:
Customer message: "I noticed my card was charged twice on October 1st for the same subscription ($19.99 each). Please refund the extra charge."

Question: Which support intent best matches this request?
Options:
(A) Duplicate charge / refund request
(B) Cancellation request
(C) Account login issue
(D) General inquiry
Answer: ("""

response = requests.post(
    "http://localhost:11434/api/generate",
    json={
        "model": "actbro/minicpm5-2b-jev",
        "prompt": prompt,
        "stream": False,
        "options": {
            "temperature": 0.1,
            "stop": ["\n", ")"]
        }
    }
)

decision = response.json()["response"].strip()
print("Selected Option: (", decision, ")", sep="")

cURL

curl http://localhost:11434/api/generate -d '{
  "model": "actbro/minicpm5-2b-jev",
  "prompt": "Context:\nRefund policy: Customers are eligible for a full refund within 30 days of purchase.\nCase: Purchase date Jan 10, refund requested Jan 24.\n\nQuestion: Is this purchase eligible for a refund?\nOptions:\n(A) Yes\n(B) No\nAnswer: (",
  "stream": false,
  "options": {
    "temperature": 0.1,
    "stop": ["\n", ")"]
  }
}'

4. Native /v1/systemone Production Serving

Note on Ollama’s /v1/systemone endpoint:
Ollama 0.35 introduced an experimental /v1/systemone endpoint with an internal allowlist currently restricted to specific built-in models.

If you need: 1. Full TypeSafe Jev API compliance (/v1/systemone with state and multi-question questions dictionary), 2. Single-pass non-autoregressive speed with shared-prefix KV caching, 3. Exact calibrated probability distributions and prior debiasing via head.pt,

Please use the native production FastAPI server provided in our official GitHub repository:

# Clone the repository
git clone https://github.com/yuting-ai/minicpm5-2b-jev
cd minicpm5-2b-jev

# Install dependencies and start server
pip install -r requirements.txt
python serve.py --port 8000

Once running, it natively serves the standard TypeSafe Jev API at http://localhost:8000/v1/systemone with complete calibration.

5. Links & Citation

• GitHub: yuting-ai/minicpm5-2b-jev
• Hugging Face: ytbai/MiniCPM5-2B-Jev
• Ollama: ollama.com/actbro/minicpm5-2b-jev