viettelsecurity-ai/security-llama3.2-3b

Model Overview

Developers	Meta
Architecture	3B parameters, dense decoder-only Transformer model
Inputs	Text, best suited for prompts in the chat format
Context length	4K tokens
Outputs	Generated text in response to input
License	MIT

Training Datasets

Our training data is an extension of the data used for security-llama3.2-3b and includes a wide variety of sources from:

1. Publicly available blogs, papers, reference from: https://github.com/PEASEC/cybersecurity_dataset.

2. Newly created synthetic, "textbook-like" data for the purpose of teaching cybersecurity (use GPT-4o).

3. Acquired academic books and Q&A datasets

Usage

Input Formats

Given the nature of the training data, security-llama3.2-3b is best suited for prompts using the chat format as follows:

<|begin_of_text|><|start_header_id|>user<|end_header_id|>
Hello!<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Hey there! How are you?<|eot_id|><|start_header_id|>user<|end_header_id|>
I'm great thanks!<|eot_id|>

With transformers

import transformers

pipeline = transformers.pipeline(
    "text-generation",
    model="viettelsecurity-ai/security-llama3.2-3b",
    model_kwargs={"torch_dtype": "auto"},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a SOC-tier3"},
    {"role": "user", "content": "What is the url phishing?"},
]

outputs = pipeline(messages, max_new_tokens=128)
print(outputs[0]["generated_text"][-1])