|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- trendmicro-ailab/Llama-Primus-Reasoning |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
# Model Card for 8Bit GGUF version of TrendMicro-Llama-Primus-Reasoning-8bit-gguf |
|
|
|
|
|
|
|
|
This model is a 8bit Quantized GGUF model of trendmicro-ailab/Llama-Primus-Reasoning |
|
|
For original model and documentation visit |
|
|
|
|
|
https://huggingface.co/trendmicro-ailab/Llama-Primus-Reasoning |
|
|
|
|
|
|
|
|
# Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training |
|
|
|
|
|
>TL;DR: Llama-Primus-Reasoning is a reasoning model distilled from the reasoning steps with reflection data generated by o1-preview on cybersecurity tasks (_Primus-Reasoning_), based on Llama-Primus-Merged. It demonstrates a 🚀**10%** improvement in security certification (CISSP). |
|
|
|
|
|
|
|
|
**🔥 For more details, please refer to the paper: [[📄Paper]](https://arxiv.org/abs/2502.11191).** |
|
|
|
|
|
## License |
|
|
This model is based on the MIT license, but you must also comply with the Llama 3.1 Community License Agreement. |
