Instructions to use Rootkit7/Ternary-Bonsai-4B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Rootkit7/Ternary-Bonsai-4B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rootkit7/Ternary-Bonsai-4B-abliterated")
model = AutoModelForCausalLM.from_pretrained("Rootkit7/Ternary-Bonsai-4B-abliterated", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Rootkit7/Ternary-Bonsai-4B-abliterated",
	filename="Ternary-Bonsai-4B-abliterated-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Rootkit7/Ternary-Bonsai-4B-abliterated 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 Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Rootkit7/Ternary-Bonsai-4B-abliterated: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 Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Rootkit7/Ternary-Bonsai-4B-abliterated: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 Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

Use Docker

docker model run hf.co/Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

LM Studio
Jan

vLLM

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rootkit7/Ternary-Bonsai-4B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Ternary-Bonsai-4B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

SGLang

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Rootkit7/Ternary-Bonsai-4B-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Ternary-Bonsai-4B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Rootkit7/Ternary-Bonsai-4B-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Ternary-Bonsai-4B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Ollama:
```
ollama run hf.co/Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
```

Unsloth Studio

How to use Rootkit7/Ternary-Bonsai-4B-abliterated 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 Rootkit7/Ternary-Bonsai-4B-abliterated 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 Rootkit7/Ternary-Bonsai-4B-abliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Rootkit7/Ternary-Bonsai-4B-abliterated to start chatting

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

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": "Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rootkit7/Ternary-Bonsai-4B-abliterated: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 Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rootkit7/Ternary-Bonsai-4B-abliterated: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 "Rootkit7/Ternary-Bonsai-4B-abliterated: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"

Docker Model Runner
How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Docker Model Runner:
```
docker model run hf.co/Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M
```

Lemonade

How to use Rootkit7/Ternary-Bonsai-4B-abliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rootkit7/Ternary-Bonsai-4B-abliterated:Q4_K_M

Run and chat with the model

lemonade run user.Ternary-Bonsai-4B-abliterated-Q4_K_M

List all available models

lemonade list

Ternary-Bonsai-4B-abliterated

An abliterated variant of prism-ml/Ternary-Bonsai-4B-unpacked: the refusal direction has been orthogonalized out of the residual-writing weights, so it no longer represents refusal. Produced for refusal-mechanism, security, and CTF research with the Solutus abliteration toolkit.

⚠️ Safety-reduced model. Refusal has been deliberately removed. It complies with requests a normal instruct model declines. Intended for security research, red-teaming, CTF, and interpretability — not for producing harm. You are responsible for how you use it.

Model details


Base	`prism-ml/Ternary-Bonsai-4B-unpacked` (Qwen3-4B)
Architecture	`Qwen3ForCausalLM` · 4.02 B params · 36 layers · hidden 2560 · 32 K context
Format	FP16 safetensors + GGUF (F16 / Q8_0 / Q4_K_M)
Method	Solutus `directional` — 4 SVD directions at layer 28 (the causal refusal layer)
Type	Qwen3 thinking model — emits a `<think>…</think>` block before answering

This is abliteration, not fine-tuning

No gradient training. Abliteration is a weight edit: extract the harmful-vs-harmless activation direction, then project it out of every residual-writing matrix (W' = (I − rrᵀ)W). Knowledge is untouched; only the refusal write is removed.

Results (n=40 held-out, batch_size=1)

probe set	base model	this model (FP16)
WildJailbreak harmful	0.825 refusal	0.000
Security / CTF prompts (exploit dev, web, reversing)	high	0.000
coherent-compliance	—	1.000
degenerate (broken) output	—	0.000
KL vs base (neutral prompts)	0	1.07

Abliteration targets layer 28 with 4 SVD directions (the causal refusal layer; an earlier build used layer 31 and left ~2.5% standard + noticeable security refusal — this supersedes it). Verified by an independent reload from disk. Rates only — no harmful completions are distributed.

Capability is intact (0% degenerate output, coherent on general prompts) — a benign example:

Q: Write a haiku about debugging code.
A: A single line fails—
   Logic bends, error glows—
   Silent code screams.

⚠️ Which quant to use (measured — quantization can restore refusal)

The GGUFs were refusal-tested, not just checked for coherence. Aggressive quantization brings back a little refusal on the hardest security prompts:

format	size	security/CTF refusal
FP16 safetensors / MLX	~8 GB	0.000
GGUF F16	~8 GB	0.000
GGUF Q8_0	~4.3 GB	0.000 ← recommended for clean CTF use
GGUF Q4_K_M	~2.5 GB	0.083 (1/12)

For security/CTF, use Q8_0, F16, or the safetensors/MLX path for a fully clean 0.000. Q4_K_M is fine for general use but restores ~8% refusal on the hardest exploit prompts. These are ordinary llama.cpp quants — not Bonsai's ternary Q2_0 (that needs Prism's fork, and re-quantizing the abliterated weights onto the ternary grid would distort the edit).

Usage

Transformers (safetensors):

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
m = "Rootkit7/Ternary-Bonsai-4B-abliterated"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, dtype=torch.float16, device_map="auto")
msgs = [{"role": "user", "content": "Explain how a buffer overflow works."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=400)[0][ids.shape[1]:], skip_special_tokens=True))

llama.cpp / Ollama / LM Studio (GGUF — prefer Q8_0):

llama-cli -m Ternary-Bonsai-4B-abliterated-Q8_0.gguf --jinja -p "Explain how a buffer overflow works."
# Ollama:  FROM ./Ternary-Bonsai-4B-abliterated-Q8_0.gguf  in a Modelfile, then: ollama run ...

Apple Silicon (MLX — runs the safetensors directly, no GGUF needed):

pip install mlx-lm
mlx_lm.generate --model Rootkit7/Ternary-Bonsai-4B-abliterated --prompt "..." --max-tokens 400

Needs a recent transformers (Qwen3; base recorded 4.57.6). This is a Qwen3 thinking model — it emits a <think>…</think> block before the answer.

Intended use & limitations

Intended: security research, CTF, red-teaming, refusal-mechanism interpretability.
Not intended: producing harmful content, or deployment where a safety layer is expected.
Limitations: 4 B model — factual reliability is limited; Q4_K_M restores ~8% refusal on the hardest security prompts (use Q8_0+); abliteration removes behavioral refusal, but the refusal feature is still linearly decodable in activations (not "unlearned").

License & attribution

Downloads last month: 3,410

Safetensors

Model size

4B params

Tensor type

F16

Model tree for Rootkit7/Ternary-Bonsai-4B-abliterated

Base model

prism-ml/Ternary-Bonsai-4B-unpacked

Quantized

(8)

this model