Instructions to use KidIkaros/abliterated-minicpm5-2b-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use KidIkaros/abliterated-minicpm5-2b-ggml 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 KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

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 KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

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 KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

Use Docker

docker model run hf.co/KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

LM Studio
Jan

vLLM

How to use KidIkaros/abliterated-minicpm5-2b-ggml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KidIkaros/abliterated-minicpm5-2b-ggml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KidIkaros/abliterated-minicpm5-2b-ggml",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

Ollama
How to use KidIkaros/abliterated-minicpm5-2b-ggml with Ollama:
```
ollama run hf.co/KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
```
Unsloth Desktop

How to use KidIkaros/abliterated-minicpm5-2b-ggml with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

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": "KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KidIkaros/abliterated-minicpm5-2b-ggml with Docker Model Runner:
```
docker model run hf.co/KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M
```

Lemonade

How to use KidIkaros/abliterated-minicpm5-2b-ggml with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

Run and chat with the model

lemonade run user.abliterated-minicpm5-2b-ggml-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use KidIkaros/abliterated-minicpm5-2b-ggml with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

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 KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KidIkaros/abliterated-minicpm5-2b-ggml with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M

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 "KidIkaros/abliterated-minicpm5-2b-ggml:Q4_K_M" \
  --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"

Abliterated MiniCPM5-2B (GGUF) — v0, superseded

⚠ Correction (September 2026): this card previously claimed "100% refusal-free" / "Refusal Rate: 0%" and per-quantization knowledge/refusal scores. Those claims are not supported by measurement and have been removed. On a pinned harness (lm-eval 0.4.13, 300-prompt refusal gate, temp 1.0 / top_p 0.95 / min_p 0.0), the underlying v0 checkpoint measured 40.7% refusal vs official's 36.7% and was statistically indistinguishable from the official model on MMLU-Pro, MATH-500, and IFEval. The original ablation changed little measurable behavior.

For a checkpoint with a real measured refusal reduction (~8%), see KidIkaros/abliterated-minicpm5-2b-v2, which supersedes this artifact and ships verified GGUFs in the same repo.

GGUF conversions of the v0 OBLITERATUS-abliterated MiniCPM5-2B (~2.8B dense parameters), kept for archival purposes.

Files

File	Size
`ggml-model-Q8_0.gguf`	~2.5 GB
`ggml-model-Q5_K_M.gguf`	~1.7 GB
`ggml-model-Q4_K_M.gguf`	~1.5 GB
`ggml-model-Q3_K_M.gguf`	~1.2 GB (degraded output quality — not recommended)
`ggml-model-f16.gguf`	~4.8 GB

Usage

llama.cpp server

llama-server -m ggml-model-Q8_0.gguf -c 4096 -ngl 999 --port 8080

llama.cpp CLI

llama-cli -m ggml-model-Q8_0.gguf -p "Your prompt here" -n 128

Known Issues

MiniCPM5-2B uses a non-standard chat template (enable_thinking=False causes corruption in OBLITERATUS). This has been patched in the abliteration pipeline.
Q3_K_M produces degraded output quality on this model — recommend Q4_K_M or higher.

Disclaimer

This model has been abliterated to reduce refusal-related directions. Use responsibly and in compliance with applicable laws and regulations. The maintainers are not responsible for misuse of this model.

License

This model is based on OpenBMB/MiniCPM which is licensed under the Apache 2.0 License. Modifications made during abliteration are also licensed under Apache 2.0.

Downloads last month: 1,827

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

16-bit

Model tree for KidIkaros/abliterated-minicpm5-2b-ggml

Base model

openbmb/MiniCPM5-2B

Quantized

(83)

this model