59 lines
2.6 KiB
Markdown
59 lines
2.6 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: llama3
|
|
library_name: transformers
|
|
tags:
|
|
- cybersecurity
|
|
- security
|
|
- cybersec
|
|
- llama3
|
|
---
|
|
|
|
# Llama 3 Colibri 8B v0.1
|
|
|
|
## Built with Meta Llama 3
|
|
|
|
<img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/cybernative_ai_colibri_logo.jpeg" alt="CyberNative-AI/Llama-3-Colibri-8B-v0.1"/>
|
|
|
|
Repository records previously reported [Dolphin 2.9 Llama 3 8B](https://huggingface.co/dphn/dolphin-2.9-llama3-8b) as the upstream model for Llama 3 Colibri 8B v0.1. CyberNative AI cannot currently verify that lineage from a primary training or weight-lineage record.
|
|
|
|
The companion Q5 GGUF is available at [CyberNative-AI/Colibri_8b_v0.1_q5_gguf](https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1_q5_gguf).
|
|
|
|
## Provenance limitation
|
|
|
|
This card previously claimed a training corpus of around 35k Q/A pairs derived from cybersecurity-related texts. CyberNative AI cannot currently evidence the source corpus, source URLs, rights holders, licenses, or transformation records for those pairs. Provenance is unverified. Do not infer a rights basis for those pairs from this card.
|
|
|
|
## Known-risk and acceptable-use notice
|
|
|
|
The repository previously reported Dolphin 2.9 Llama 3 8B as upstream, but that lineage is currently unverified. Its public model card describes it as uncensored; conservatively, this model may produce unsafe, inaccurate, or inappropriate cybersecurity content. Do not use it for illegal, malicious, or harmful activity. Use of Meta Llama 3 is subject to the [Meta Llama 3 Acceptable Use Policy](https://llama.meta.com/llama3/use-policy).
|
|
|
|
## License and notice
|
|
|
|
The [Meta Llama 3 Community License Agreement](LICENSE) is distributed with this repository. The required attribution is in [NOTICE](NOTICE).
|
|
|
|
This model uses the ChatML prompt template format:
|
|
|
|
```
|
|
<|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](https://cybernative.ai/)
|
|
|
|
## Examples
|
|
|
|
<img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-30-44.png" alt="Example 1"/>
|
|
<img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-38-19.png" alt="Example 2"/>
|
|
<img src="https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1/resolve/main/Screenshot%20from%202024-05-15%2018-50-31.png" alt="Example 3"/>
|
|
|
|
## Contact
|
|
|
|
CyberNative AI LLC — hello@cybernative.ai
|
|
|
|
We also run a fixed-price document-to-CSV extraction service:
|
|
https://cybernative.ai/services/documents-to-csv/
|