AdarshRL/llama-3.1-70b-terraform-architect-adapter

Llama 3.1 70B - Terraform Principal Architect

This is a fine-tuned LoRA adapter for Llama 3.1 70B Instruct, specialized in generating high-quality, production-ready Google Cloud Terraform code.

⚠️ Note on Model Size

This is the 70B parameter version of the architect. It requires significant VRAM (40GB+) to run, even with 4-bit quantization.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = "meta-llama/Llama-3.1-70B-Instruct"
adapter_id = "AdarshRL/Llama-3.1-70B-Terraform-Architect"

model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto", load_in_4bit=True)
model = PeftModel.from_pretrained(model, adapter_id)