A 1 billion-parameter language model fine-tuned specifically for the domain of building engineering — covering HVAC, structural design, MEP systems, building codes, and sustainability.
Key Specifications:
Model Size: 1B parameters
Quantization: 4-bit (INT4)
Frameworks: PyTorch & Hugging Face Transformers
Deployment: Docker, Kubernetes, on-device inference with vLLM
Training data: Building codes, HVAC manuals, structural engineering papers, energy modeling documents
Why It Matters
ndustry-Specific Insights
Provides accurate and fast responses to building engineering queries — from HVAC sizing to code compliance.
Optimized for Lightweight Deployment
Runs efficiently on edge devices or inside CI/CD pipelines for engineering workflows.
Quick start example
Get Started
🔗 GitHub Repository
For more details on how to use it and for downloading it you can find the model on GitHub which you can find below