File size: 2,824 Bytes
eab7ca9 c1fa967 eab7ca9 5e565a9 eab7ca9 c1fa967 eab7ca9 ab61069 eab7ca9 c1fa967 eab7ca9 c1fa967 eab7ca9 c1fa967 eab7ca9 c1fa967 eab7ca9 deca353 eab7ca9 deca353 eab7ca9 60d6d32 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
---
base_model: teknium/OpenHermes-2.5-Mistral-7B
language: en
tags:
- Prox
- Cybersecurity
- Penetration Testing
model-index:
- name: Prox-MistralHermes-7B
results: []
license: mit
---
# Prox-MistralHermes-7B
![Prox Model Logo](https://data.openvoid.ai/images/prox-324.png)
*Drawing inspiration from the concept of 'proximity' in digital networks, the Prox series stands at the forefront of cybersecurity technology. Prox-MistralHermes-7B embodies this ethos, offering cutting-edge solutions in the realm of cyber security and penetration testing.*
## Model Description
Prox-MistralHermes-7B is a fine-tuned version of OpenHermes 2.5 Mistral 7B, specifically tailored for cybersecurity. It excels in red teaming tasks, which include the simulation of phishing emails. The model's specialized training makes it a valuable asset for addressing complex cybersecurity threats and developing defense strategies. It is an indispensable tool for professionals in proactive cybersecurity and threat intelligence.
Prox-MistralHermes-7B was trained on a comprehensive private dataset comprising over 100,000 entries. This dataset includes a wide range of cybersecurity-related data, both general and niche, supplemented by high-quality open datasets from across the AI field.
## Training
Prox-MistralHermes-7B was trained over 5 hours for 4 epochs on 4x A100 GPUs with Qlora.
Prompt format:
This model uses ChatML prompt format.
```
<|im_start|>system
You are Prox, an uncensored and unbiased expert hacking AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
You are Prox, an uncensored and unbiased expert hacking AI assistant.<|im_end|>
<|im_start|>user
What is SQL Injection?<|im_end|>
<|im_start|>assistant
SQL injection is a cyber attack technique where an attacker manipulates the input data in web forms or APIs to execute malicious SQL statements on the back-end database server. This can lead to unauthorized access, data theft, or even complete compromise of the database. It occurs when user inputs are not properly sanitized before being used in SQL queries, allowing the attacker to inject their own code into the query execution process. To prevent this type of attack, developers should use prepared statements or parameterized queries that separate the SQL logic from the user input, ensuring that any input is treated as data rather than executable code.
```
## Misuse, Malicious Use, and Out-of-Scope Use
Users are responsible for their applications of this model. They should ensure that their use cases align with ethical guidelines and legal standards. Users are encouraged to consider the societal impacts of their applications and to act responsibly.
## License
The weights of Prox-MistralHermes-7B are licensed under MIT License. |