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
Download the GGUF file.
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."
Run via Ollama: ollama create infragenie -f Modelfile
