Instructions to use HarshG05/InfraGenie-Azure-Expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarshG05/InfraGenie-Azure-Expert with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("HarshG05/InfraGenie-Azure-Expert", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use HarshG05/InfraGenie-Azure-Expert 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 HarshG05/InfraGenie-Azure-Expert:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HarshG05/InfraGenie-Azure-Expert:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HarshG05/InfraGenie-Azure-Expert:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HarshG05/InfraGenie-Azure-Expert: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 HarshG05/InfraGenie-Azure-Expert:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HarshG05/InfraGenie-Azure-Expert: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 HarshG05/InfraGenie-Azure-Expert:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HarshG05/InfraGenie-Azure-Expert:Q4_K_M

Use Docker

docker model run hf.co/HarshG05/InfraGenie-Azure-Expert:Q4_K_M

LM Studio
Jan
Ollama
How to use HarshG05/InfraGenie-Azure-Expert with Ollama:
```
ollama run hf.co/HarshG05/InfraGenie-Azure-Expert:Q4_K_M
```

Unsloth Studio

How to use HarshG05/InfraGenie-Azure-Expert 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 HarshG05/InfraGenie-Azure-Expert 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 HarshG05/InfraGenie-Azure-Expert to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HarshG05/InfraGenie-Azure-Expert to start chatting

How to use HarshG05/InfraGenie-Azure-Expert with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HarshG05/InfraGenie-Azure-Expert: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": "HarshG05/InfraGenie-Azure-Expert:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use HarshG05/InfraGenie-Azure-Expert with Docker Model Runner:
```
docker model run hf.co/HarshG05/InfraGenie-Azure-Expert:Q4_K_M
```

Lemonade

How to use HarshG05/InfraGenie-Azure-Expert with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HarshG05/InfraGenie-Azure-Expert:Q4_K_M

Run and chat with the model

lemonade run user.InfraGenie-Azure-Expert-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use HarshG05/InfraGenie-Azure-Expert with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HarshG05/InfraGenie-Azure-Expert: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 HarshG05/InfraGenie-Azure-Expert:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use HarshG05/InfraGenie-Azure-Expert with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HarshG05/InfraGenie-Azure-Expert: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 "HarshG05/InfraGenie-Azure-Expert: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"

InfraGenie-Azure-Expert / README.md

HarshG05

Upload README.md with huggingface_hub

02311af verified 16 days ago

preview code

Raw

History Blame Contribute Delete

1.31 kB

	---
	library_name: transformers
	tags:
	- unsloth
	- azure
	- terraform
	- bicep
	- infrastructure-as-code
	base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
	---

	# InfraGenie-Azure-Expert

	InfraGenie is a specialized AI assistant fine-tuned for Azure Infrastructure management. It is designed to assist DevOps engineers and Architects in generating and reasoning about Cloud Infrastructure.

	## Model Details
	- Developed by: HarshG05
	- Model type: Causal Language Model (Fine-tuned Qwen2.5-Coder-7B)
	- Language(s): English, Terraform, Bicep, ARM
	- Finetuned from model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit

	## Uses
	- Direct Use: Generating Terraform modules and Bicep templates for Azure.
	- Routing Logic: Automatically routes simple tasks to Bicep and complex infrastructure patterns to Terraform.

	## Training Details
	- Framework: Unsloth & QLoRA (4-bit quantization)
	- Hardware: Tesla T4 GPU (Google Colab)
	- Data Sources: Microsoft Learn, Terraform Registry, Azure Architecture Center

	## How to Get Started
	1. Download the GGUF file.
	2. Create a Modelfile with the following system prompt:
	`SYSTEM "You are an Azure Infrastructure expert. Route simple requests to Bicep and complex ones to Terraform."`
	3. Run via Ollama: `ollama create infragenie -f Modelfile`