metadata
library_name: transformers
tags:
- cybersecurity
- security
- cybersec
- base
- llama3
license: llama3
language:
- en
Colibri_8b_v0.1
![CyberNative-AI/Colibri_8b_v0.1](https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/cybernative_ai_colibri_logo.jpeg)
Colibri: Conversational CyberSecurity Model
GGUF Quant available here: CyberNative-AI/Colibri_8b_v0.1_q5_gguf
Colibri_8b_v0.1 is a conversational model for cybersecurity fine-tuned from the awesome dolphin-2.9-llama3-8b. (llama-3-8b -> cognitivecomputations/dolphin-2.9-llama3-8b -> CyberNative-AI/Colibri_8b_v0.1)
We derived our training dataset by creating Q/A pairs from a huge amount of cybersecurity related texts.
v0.1 trained for 3 epochs using around 35k Q/A pairs FFT on all parameters using a single A100 80gb for 3 hours.
This model is using ChatML prompt template format.
example:
<|im_start|>system
You are Colibri, an advanced cybersecurity AI assistant developed by CyberNative AI.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Provided by CyberNative AI
ANY ILLEGAL AND/OR UNETHICAL USE IS NOT PERMITTED!