llmagent4incident-response

LLM Agent for Incident Response

This repository contains the LoRA adapter weights of a language model fine-tuned for incident-response planning and recovery-action generation.

Base Model

This adapter must be loaded on top of:

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

Adapter Details

• Fine-tuning method: LoRA
• Task type: Causal language modeling
• LoRA rank: 64
• LoRA alpha: 128
• LoRA dropout: 0.05
• Target modules: q_proj, v_proj
• Released checkpoint: 850

Repository Files

• adapter_model.safetensors: LoRA adapter weights
• adapter_config.json: LoRA adapter configuration
• README.md: model documentation

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
adapter_name = "GYR1-determine/llmagent4incident-response"

tokenizer = AutoTokenizer.from_pretrained(base_model_name)

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    device_map="auto",
)

model = PeftModel.from_pretrained(base_model, adapter_name)