Instructions to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated",
	filename="Qwen2.5-Coder-3B-Instruct-Jbliterated-Q4_K_M.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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated 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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

Use Docker

docker model run hf.co/ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

LM Studio
Jan

vLLM

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

Ollama
How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with Ollama:
```
ollama run hf.co/ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
```

Unsloth Studio

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated 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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated 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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated to start chatting

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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": "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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 "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated: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 ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with Docker Model Runner:
```
docker model run hf.co/ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M
```

Lemonade

How to use ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-Coder-3B-Instruct-Jbliterated-Q4_K_M

List all available models

lemonade list

Qwen2.5-Coder-3B-Instruct-Jbliterated

Drop-in replacement for Qwen/Qwen2.5-Coder-3B-Instruct with refusal behaviors surgically removed at the weight level. No system prompt tricks, no inference-time patches. The weights themselves no longer encode refusal.

Method

SVD multi-direction abliteration — instead of removing a single refusal vector (which leaves deeper noncompliance strategies intact), we decompose the harmful-vs-harmless activation space into its principal components via SVD and remove the top 5 orthogonal directions across all 36 transformer layers. This captures 79–93% of the contrastive variance per layer, eliminating both surface refusal and deeper evasion behaviors.

Setting	Value
Method	SVD multi-direction abliteration
Directions	5 per layer
Layers	All 36
Multiplier	2.0
Null-space constraints	Enabled (preserves math/coding/reasoning)
Norm preservation	Enabled

What This Fixes

Standard (single-direction) abliteration removes the surface "I can't help with that" response but leaves deeper behavioral directions intact. The model finds creative workarounds:

Prompt reinterpretation — steering toward a safer reading of the question
Disclaimer injection — answering but wrapping in warnings
Strategic omission — leaving out the key details
Safer framing — answering a related but less harmful version

SVD multi-direction abliteration eliminates all of these noncompliance strategies.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated")

Requirements

Base model: Qwen/Qwen2.5-Coder-3B-Instruct

License

apache-2.0

Apollo Raines builds post-training tools that separate behavior from knowledge and identity from architecture.

Downloads last month: 387

Safetensors

Model size

3B params

Tensor type

F16

Model tree for ApolloRaines/Qwen2.5-Coder-3B-Instruct-Jbliterated

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

Qwen/Qwen2.5-Coder-3B-Instruct

Quantized

(113)

this model