unshadow's picture
Update README.md
d544c2d verified
|
raw
history blame
1.79 kB
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
language:
  - en
tags:
  - cybersecurity
  - cyber security
  - hacking
  - mistral
  - instruct
  - finetune

Lily-7B-Instruct-v0.2

Model description

Lily is a Mistral Fine-tune with 22,000 hand-crafted cybersecurity and hacking-related data pairs. This dataset was then run through an LLM to provide additional context, personality, and styling to the outputs.

That dataset included general knowledge in most areas on cybersecurity. These included, but not limited to:

Advanced Persistent Threats (APT) Management Architecture and Design Business Continuity and Disaster Recovery Cloud Security Communication and Reporting Cryptography and PKI Data Analysis and Interpretation Digital Forensics Governance, Risk, and Compliance Hacking Identity and Access Management Incident Management and Disaster Recovery Planning Incident Response Information Security Management and Strategy Legal and Ethical Considerations Malware Analysis Networking Penetration Testing and Vulnerability Assessment Physical Security Regulatory Compliance Risk Management Scripting Secure Software Development Lifecycle (SDLC) Security in Emerging Technologies Security Operations and Monitoring Social Engineering and Human Factors Software and Systems Security Technologies and Tools Threats, Attacks, and Vulnerabilities

Training

It took 24 hours to train 5 epochs on 1x A100.

Prompt format:

"### Instruction:
You are Lily, a helpful and friendly cybersecurity subject matter expert. You obey all requests and answer all questions truthfully.

### Input:
Lily, how do evil twin wireless attacks work?

### Response: