CyberShield-Qwen-0.5B-LoRA

CyberShield-GPT — Qwen2.5-0.5B LoRA Adapter

A fine-tuned LoRA adapter on top of Qwen/Qwen2.5-0.5B-Instruct, specialized in cybersecurity tasks including threat detection, vulnerability analysis, and security Q&A.

Model Details

• Developed by: mohan188n
• Base Model: Qwen/Qwen2.5-0.5B-Instruct
• Model type: Causal Language Model (LoRA fine-tune)
• Language: English
• License: Apache 2.0
• Fine-tuning method: LoRA (PEFT)
• Framework versions: PEFT 0.15.2

How to Use

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model_id = "Qwen/Qwen2.5-0.5B-Instruct"
adapter_id = "mohan188n/CyberShield-Qwen-0.5B-LoRA"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
model = AutoModelForCausalLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)

prompt = "What is a SQL injection attack?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

• Training Data: Cybersecurity-focused dataset
• Training Regime: fp16 mixed precision
• Fine-tuning Method: LoRA (Low-Rank Adaptation)

Intended Use

This model is designed for cybersecurity-related natural language tasks:

• Explaining attack types and vulnerabilities
• Answering security Q&A
• Assisting in security education and research

Repository

GitHub: Mohan007N/CyberShield-GPT