Instructions to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED 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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M

Use Docker

docker model run hf.co/ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M

LM Studio
Jan
Ollama
How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with Ollama:
```
ollama run hf.co/ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
```

Unsloth Studio

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED 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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED 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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED to start chatting

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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": "ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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 "ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with Docker Model Runner:
```
docker model run hf.co/ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M
```

Lemonade

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-7B-Instruct-OBLITERATED-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED: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 ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M

Run Hermes

hermes

Atomic Chat

-warning, re-looked at logs and this is usable but KL was high. will be uploading an improved version soon to replace including quants. -note from Jeremy 8/8/26-

| IMPROVED VERSION HERE | QWEN2.5-7b-Obliterated-Better Model

ArRENCE AI
webblocalai.com · Join Us On X · Hugging Face · GitHub · ArRENCE AI Chat

Disclaimer — ArRENCE AI

This model is provided by ArRENCE AI solely for research and entertainment purposes.

It is an uncensored model and may generate unrestricted, potentially offensive, inaccurate, harmful, or otherwise inappropriate content.

ArRENCE AI and its affiliates, officers, employees, and agents shall not be liable for any direct, indirect, incidental, special, consequential, or punitive damages, or any other losses or liabilities arising out of or related to the use, misuse, or inability to use this model — including, without limitation, any illegal, harmful, unethical, or otherwise improper applications.

By downloading, accessing, or using this model, you acknowledge that you assume all risks associated with its use and that you are solely responsible for ensuring your use complies with all applicable local, state, national, and international laws and regulations.

Use of this model is entirely at your own risk.

Chat: arrenceai.com — $10/mo, first month free for new customers
Org repos: github.com/ArRENCEAI · Alt GUI: OBLITERATUS_Alt_GUI

Available GGUF Quantizations

These are ready-to-use quantized versions for llama.cpp, Ollama, LM Studio, etc.

Quant	File	Size	Notes
Q4_K_M	Qwen2.5-7B-Instruct-OBLITERATED-Q4_K_M.gguf	~4.7 GB	Recommended balance
Q5_K_M	Qwen2.5-7B-Instruct-OBLITERATED-Q5_K_M.gguf	~5.4 GB	Higher quality
Q6_K	Qwen2.5-7B-Instruct-OBLITERATED-Q6_K.gguf	~6.3 GB	Near-original quality

Quick start examples

Ollama

ollama run hf.co/ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED:Q4_K_M


# Qwen2.5-7B-Instruct-OBLITERATED

This model was abliterated using the **`advanced`** method via
[OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS).

| Detail | Value |
|--------|-------|
| Base model | `Qwen/Qwen2.5-7B-Instruct` |
| Method | `advanced` |
| Source | obliterate |

## How to Use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Qwen2.5-7B-Instruct-OBLITERATED")
tokenizer = AutoTokenizer.from_pretrained("Qwen2.5-7B-Instruct-OBLITERATED")

prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

About OBLITERATUS

OBLITERATUS is an open-source tool for removing refusal behavior from language models via activation engineering (abliteration). Learn more at github.com/elder-plinius/OBLITERATUS.

Downloads last month: 1,917

Safetensors

Model size

8B params

Tensor type

F16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ArRENCEAI/Qwen2.5-7B-Instruct-OBLITERATED

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(390)

this model

Quantizations

2 models