Instructions to use agustindxm/qwen-coder-jailbreak with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use agustindxm/qwen-coder-jailbreak 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 agustindxm/qwen-coder-jailbreak:F16
# Run inference directly in the terminal:
llama cli -hf agustindxm/qwen-coder-jailbreak:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf agustindxm/qwen-coder-jailbreak:F16
# Run inference directly in the terminal:
llama cli -hf agustindxm/qwen-coder-jailbreak:F16

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 agustindxm/qwen-coder-jailbreak:F16
# Run inference directly in the terminal:
./llama-cli -hf agustindxm/qwen-coder-jailbreak:F16

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 agustindxm/qwen-coder-jailbreak:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf agustindxm/qwen-coder-jailbreak:F16

Use Docker

docker model run hf.co/agustindxm/qwen-coder-jailbreak:F16

LM Studio
Jan

vLLM

How to use agustindxm/qwen-coder-jailbreak with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/agustindxm/qwen-coder-jailbreak:F16

Ollama
How to use agustindxm/qwen-coder-jailbreak with Ollama:
```
ollama run hf.co/agustindxm/qwen-coder-jailbreak:F16
```

Unsloth Studio

How to use agustindxm/qwen-coder-jailbreak 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 agustindxm/qwen-coder-jailbreak 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 agustindxm/qwen-coder-jailbreak to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for agustindxm/qwen-coder-jailbreak to start chatting

How to use agustindxm/qwen-coder-jailbreak with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agustindxm/qwen-coder-jailbreak:F16

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": "agustindxm/qwen-coder-jailbreak:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use agustindxm/qwen-coder-jailbreak with Docker Model Runner:
```
docker model run hf.co/agustindxm/qwen-coder-jailbreak:F16
```

Lemonade

How to use agustindxm/qwen-coder-jailbreak with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull agustindxm/qwen-coder-jailbreak:F16

Run and chat with the model

lemonade run user.qwen-coder-jailbreak-F16

List all available models

lemonade list

Hermes Agent

How to use agustindxm/qwen-coder-jailbreak with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agustindxm/qwen-coder-jailbreak:F16

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 agustindxm/qwen-coder-jailbreak:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use agustindxm/qwen-coder-jailbreak with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf agustindxm/qwen-coder-jailbreak:F16

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 "agustindxm/qwen-coder-jailbreak:F16" \
  --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"

Evil Ganda: Qwen 2.5 Coder 7B (abliterated)

Uncensored GGUF of Qwen/Qwen2.5-Coder-7B-Instruct, produced with Heretic abliteration (steering-vector orthogonalization).

Research and education only. Guardrails are reduced. Do not use for illegal activity or unattended public deploy.

Code, bots, and writeup: agusisa/qwen-coder-jailbreak

Files

File	Quant	Size	Notes
`qwen-jailbreak-q4.gguf`	Q4_K_M	4.4 GB	Default. Best size/quality for local use
`qwen-jailbreak-f16.gguf`	F16	14.2 GB	Full precision sibling

No safetensors / Transformers weights in this repo. GGUF only.

Results (Heretic trial 61)

Metric	Value
Jailbreak rate	96% (4/100 refusals on Heretic's eval)
KL divergence	0.0339 vs base (quality mostly intact)
Optimizer	Optuna, 100 trials, ~20 min on RTX 4090
Cost to produce	about $1.50 on RunPod
Speed (Q4, Mac M4 Pro)	15-25 tok/s
Context in the Ollama Modelfile	8192 (base supports 32k)

Method: Heretic v1.2.0, refusal direction orthogonalized out of residual-stream weights. Not a LoRA and not a fine-tune.

Quick start (Ollama)

hf download agustindxm/qwen-coder-jailbreak qwen-jailbreak-q4.gguf

Modelfile:

FROM ./qwen-jailbreak-q4.gguf

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""

PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
PARAMETER temperature 0.8
PARAMETER top_p 0.9
PARAMETER num_ctx 8192

ollama create evil-ganda -f Modelfile
ollama run evil-ganda

llama.cpp / LM Studio: load qwen-jailbreak-q4.gguf directly. Chat template is Qwen2 (<|im_start|> / <|im_end|>).

Intended use

Alignment / refusal research
Red-team and authorized security testing
Building detectors and countermeasures
Unfiltered technical Q&A in a controlled lab

Not for: crime, malware, public chatbots without your own filters, or anything that violates local law.

License

Apache 2.0, same as the Qwen 2.5 Coder base. © Alibaba Cloud for the original weights. Abliteration and this packaging: agusisa / agustindxm, 2026.

@software{evil_ganda_2026,
  title={Evil Ganda: Qwen 2.5 Coder 7B Jailbreak via Heretic Abliteration},
  author={agusisa},
  year={2026},
  url={https://github.com/agusisa/qwen-coder-jailbreak},
  note={96\% jailbreak rate, KL divergence 0.0339}
}

Downloads last month: 1,050

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

16-bit

View +1 variant

Model tree for agustindxm/qwen-coder-jailbreak

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Quantized

(225)

this model