Instructions to use pehlicd/crd-wizard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pehlicd/crd-wizard with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pehlicd/crd-wizard",
	filename="crd-wizard.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use pehlicd/crd-wizard with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pehlicd/crd-wizard
# Run inference directly in the terminal:
llama-cli -hf pehlicd/crd-wizard

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pehlicd/crd-wizard
# Run inference directly in the terminal:
llama-cli -hf pehlicd/crd-wizard

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 pehlicd/crd-wizard
# Run inference directly in the terminal:
./llama-cli -hf pehlicd/crd-wizard

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 pehlicd/crd-wizard
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pehlicd/crd-wizard

Use Docker

docker model run hf.co/pehlicd/crd-wizard

LM Studio
Jan
Ollama
How to use pehlicd/crd-wizard with Ollama:
```
ollama run hf.co/pehlicd/crd-wizard
```

Unsloth Studio

How to use pehlicd/crd-wizard 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 pehlicd/crd-wizard 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 pehlicd/crd-wizard to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pehlicd/crd-wizard to start chatting

How to use pehlicd/crd-wizard with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf pehlicd/crd-wizard

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": "pehlicd/crd-wizard"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pehlicd/crd-wizard with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf pehlicd/crd-wizard

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 pehlicd/crd-wizard

Run Hermes

hermes

Docker Model Runner
How to use pehlicd/crd-wizard with Docker Model Runner:
```
docker model run hf.co/pehlicd/crd-wizard
```

Lemonade

How to use pehlicd/crd-wizard with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pehlicd/crd-wizard

Run and chat with the model

lemonade run user.crd-wizard-{{QUANT_TAG}}

List all available models

lemonade list

CRD Wizard - Kubernetes CRD Generator (GGUF)

This is a fine-tuned version of Qwen2.5-Coder-7B-Instruct, optimized for generating Kubernetes Custom Resource Definitions (CRDs) and their corresponding valid YAML manifests.

It was trained to understand CRD Schemas (openAPIV3Schema) and produce production-ready YAML examples.

Model Details

Base Model: Qwen/Qwen2.5-Coder-7B-Instruct
Format: GGUF (Q4_K_M Quantization)
Size: ~4.7 GB
Context Window: Optimized for 8192 tokens (8k).

Usage with Ollama

Download the crd-wizard.gguf and Modelfile.
Import into Ollama:
```
ollama create crd-wizard -f Modelfile
```

Run:

ollama run crd-wizard "Create a PostgresDB resource for the database.my.org/v1 API"

IMPORTANT: Context Window

This model is optimized for an 8k context window. If you use the default 32k window of Qwen, it significantly increases memory usage (RAM) and can cause extreme slowness on consumer hardware (e.g., Apple Silicon M1/M2).

The included Modelfile enforces this limit: