A2124/susan-roofing-llm

Susan AI - Roofing Assistant

Conversational AI assistant specialized in roofing sales, insurance claims, and damage assessment.

Model Details

• —Base Model: Llama 3.1 8B Instruct
• —Training Data: 122 conversational examples from Roof ER
• —Fine-tuning: LoRA with 4-bit quantization
• —Response Style: Natural, conversational (like GPT/Sonnet)

Training Dataset

• —Sales scripts and objection handling
• —Email templates for insurance claims
• —Building codes (VA, MD, PA)
• —GAF warranty requirements
• —Insurance argument strategies

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("A2124/susan-roofing-llm")
tokenizer = AutoTokenizer.from_pretrained("A2124/susan-roofing-llm")

prompt = "How do I handle a double layer denial?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=500)
response = tokenizer.decode(outputs[0])
print(response)

Training Status

🚧 Training in progress...

Check back soon for the trained model!