Prox-1.0-GPT-6.7B

Prox-1.0-GPT-6.7B

Model Description

Prox-1.0-GPT-6.7B is a fine-tuned version of Cerebras-GPT-6.7B, specifically tailored for cybersecurity. It has been trained on the Prox V1 dataset and incorporates high-quality open datasets from various sources within the AI community. Additionally, it has been equipped with basic chat abilities through training on the Dolphin and OpenHermes datasets.

Training

Prox-1.0-GPT-6.7B was trained over 12 hours for 4 epochs on 8x A100 GPUs using Qlora.

Prompt format: This model uses ChatML prompt format.

<|im_start|>system
You are Prox, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are Prox, a helpful AI assistant.
<|im_start|>user
What is SQL Injection?<|im_end|>
<|im_start|>assistant

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-1.0-GPT-6.7B are licensed under version 2.0 of the Apache License.