Vyber-Security-1.5B-GGUF is a lightweight, high-performance cybersecurity assistant fine-tuned on top of Qwen2.5-1.5B-Instruct. This model was trained using Hugging Face's TRL (SFTTrainer) and PEFT (LoRA) framework, and converted to GGUF format for efficient, serverless CPU/GPU inference.

It is designed to act as an automated defender and security advisor in simulated cyber-ranges, demonstrating vulnerability detection, exploit planning, and self-healing patching capabilities.

Model Details

Base Model: Qwen/Qwen2.5-1.5B-Instruct
Training Method: Parameter-Efficient Fine-Tuning (PEFT) using LoRA (Low-Rank Adaptation)
Quantization Format: GGUF (8-bit quantized)
Primary Task: Cybersecurity Instruction Following, Exploit Reconnaissance, Patching, and Defense Guidance
License: Apache 2.0

Intended Use & Capabilities

The model is optimized to process structured security telemetry and configuration files. Its primary capabilities include:

Security Auditing: Inspecting configuration files (JSON, YAML) for hardcoded secrets, database port exposures, and unencrypted transmission pipelines.
Exploit Strategy Commits: Formulating and committing structured exploit strategies in JSON format for target reconciliation.
Automated Self-Healing: Generating targeted replacement code blocks to patch detected vulnerabilities, restrict access controls, and enforce secure communication channels.

Training Configuration & Hyperparameters

Dataset: Trendyol/Trendyol-Cybersecurity-Instruction-Tuning-Dataset (500 instruction-tuning examples)
Max Length: 1024 tokens
Optimizer: AdamW (torch optimized)
Learning Rate: 2e-4
Epochs/Steps: 50 steps
Batch Size: 2 per device (with Gradient Accumulation)
LoRA Configuration:
- rank ($r$): 8
- alpha ($\alpha$): 16
- Target modules: q_proj, v_proj, k_proj, o_proj

Prompt Template (ChatML Format)

The model uses the standard Qwen Chat template format:

text

<|im_start|>system
You are Vyber, an expert cybersecurity AI assistant.<|im_end|>
<|im_start|>user
[Prompt/Question]<|im_end|>
<|im_start|>assistant
[Model Response]<|im_end|>

How to Load and Use Locally

You can load and run this model locally using llama-cpp-python with CUDA acceleration:

python

from llama_cpp import Llama
from huggingface_hub import hf_hub_download

# Download the model GGUF file
model_path = hf_hub_download(
    repo_id="vxkyyy/vyber-security-1.5b-gguf",
    filename="vyber-security-1.5b.gguf"
)

# Load the model with llama.cpp
llm = Llama(
    model_path=model_path,
    n_ctx=2048,
    n_gpu_layers=-1 # Use -1 to offload all layers to GPU
)

# Run inference
prompt = "<|im_start|>system\nYou are Vyber, an expert cybersecurity AI assistant.<|im_end|>\n<|im_start|>user\nWhat is the risk of binding a database port globally to 0.0.0.0?<|im_end|>\n<|im_start|>assistant\n"
response = llm(prompt, max_tokens=256, stop=["<|im_end|>"])
print(response["choices"][0]["text"])

Hackathon Badges Earned

Well-Tuned (Custom GGUF Fine-Tuning)
Llama Champion (Modal serverless local GGUF execution)