Instructions to use turnercore/minicpm5-automaticity-v7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use turnercore/minicpm5-automaticity-v7 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="turnercore/minicpm5-automaticity-v7",
	filename="MiniCPM5_AUTOMATICITY_V7_Q4.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use turnercore/minicpm5-automaticity-v7 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 turnercore/minicpm5-automaticity-v7
# Run inference directly in the terminal:
llama cli -hf turnercore/minicpm5-automaticity-v7

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf turnercore/minicpm5-automaticity-v7
# Run inference directly in the terminal:
llama cli -hf turnercore/minicpm5-automaticity-v7

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 turnercore/minicpm5-automaticity-v7
# Run inference directly in the terminal:
./llama-cli -hf turnercore/minicpm5-automaticity-v7

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 turnercore/minicpm5-automaticity-v7
# Run inference directly in the terminal:
./build/bin/llama-cli -hf turnercore/minicpm5-automaticity-v7

Use Docker

docker model run hf.co/turnercore/minicpm5-automaticity-v7

LM Studio
Jan
Ollama
How to use turnercore/minicpm5-automaticity-v7 with Ollama:
```
ollama run hf.co/turnercore/minicpm5-automaticity-v7
```

Unsloth Studio

How to use turnercore/minicpm5-automaticity-v7 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for turnercore/minicpm5-automaticity-v7 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for turnercore/minicpm5-automaticity-v7 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for turnercore/minicpm5-automaticity-v7 to start chatting

How to use turnercore/minicpm5-automaticity-v7 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/minicpm5-automaticity-v7

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "turnercore/minicpm5-automaticity-v7"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use turnercore/minicpm5-automaticity-v7 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/minicpm5-automaticity-v7

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 turnercore/minicpm5-automaticity-v7

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use turnercore/minicpm5-automaticity-v7 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf turnercore/minicpm5-automaticity-v7

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 "turnercore/minicpm5-automaticity-v7" \
  --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"

Docker Model Runner
How to use turnercore/minicpm5-automaticity-v7 with Docker Model Runner:
```
docker model run hf.co/turnercore/minicpm5-automaticity-v7
```

Lemonade

How to use turnercore/minicpm5-automaticity-v7 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull turnercore/minicpm5-automaticity-v7

Run and chat with the model

lemonade run user.minicpm5-automaticity-v7-{{QUANT_TAG}}

List all available models

lemonade list

minicpm5-automaticity-v7

File size: 1,692 Bytes

---
license: apache-2.0
base_model: openbmb/MiniCPM5-1B
tags:
- function-calling
- tool-use
- minicpm
- automaticity
---

# MiniCPM5 Automaticity V7

Public release of the MiniCPM5 automaticity V7 LoRA and merged GGUF exports.

The training data and benchmark repos are private because future rows/results may contain real tool-call traces.
The included HTML report and benchmark dataset repo compare:

- MiniCPM5_Base
- MiniCPM5_Base + AUTOMATICITY_V7_LORA_ADAPTER
- MiniCPM5_AUTOMATICITY_V7_Q4
- MiniCPM5_AUTOMATICITY_V7_Q8
- FunctionGemma_AUTOMATICITY_V7_Q8

MiniCPM tool-call fine-tuning targets MiniCPM XML function calls rather than JSON.

## Automaticity benchmark v1

Frozen local benchmark: `/home/turnercore/automaticity-benchmark-v1/automaticity-hard-v1.jsonl`

Canonical benchmark repo: `turnercore/automaticity-benchmark-v1` (private)

| Run | Exact | Tool name | Arguments | No-op recall | p50 latency | p95 latency |
| --- | ---: | ---: | ---: | ---: | ---: | ---: |
| FunctionGemma_AUTOMATICITY_V7_Q8 | 82/92 (89.1%) | 96.7% | 90.2% | 94.7% | 180 ms | 568 ms |
| MiniCPM5_Base | 78/92 (84.8%) | 92.4% | 87.0% | 86.8% | 701 ms | 2,070 ms |
| MiniCPM5_Base + AUTOMATICITY_V7_LORA_ADAPTER | 59/92 (64.1%) | 67.4% | 75.0% | 21.1% | 316 ms | 478 ms |
| MiniCPM5_AUTOMATICITY_V7_Q8 | 60/92 (65.2%) | 69.6% | 75.0% | 26.3% | 151 ms | 248 ms |
| MiniCPM5_AUTOMATICITY_V7_Q4 | 54/92 (58.7%) | 64.1% | 67.4% | 13.2% | 141 ms | 226 ms |

The V7 MiniCPM fine-tune is not promoted. It learned the XML output shape and is fast when baked to GGUF, but it overcalls no-op, negated, hypothetical, deferred, and incomplete prompts. `AUTOMATICITY_V8` adds no-op hardening rows for the next run.