WaiLwin/network-model-adapter

Network Configuration Analysis LoRA Adapter

LoRA adapter for network configuration analysis, optimized for memory efficiency.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-bnb-4bit")
tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3.2-3b-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "WaiLwin/network-model-adapter")

Training Details

• Optimized for Google Colab memory constraints
• LoRA Rank: 8, Alpha: 8
• Max Sequence Length: 1024