chYassine/AMAN-7b-v01

Model Details

Model Description
Developed by: Yassine Chagna & Ahmed Ouidani
Model type: Cyberattack Detection
Language(s) (NLP): English
License: apache 2.0
Finetuned from model: mistralai/Mistral-7B-Instruct-v0.3

Uses

Direct Use
This model can be directly used for monitoring web access logs to detect potential cyber attacks.

Downstream Use
The model can be adapted for other types of logs and cyberattack detection scenarios.

Out-of-Scope Use
This model is not designed for general-purpose NLP tasks unrelated to cyberattack detection.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. More information is needed for further recommendations.

Summary

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: A100 GPU

Technical Specifications [optional]

Model Architecture and Objective
The model uses the architecture of mistralai/Mistral-7B-Instruct-v0.3, fine-tuned for cyberattack detection on web access logs.

Compute Infrastructure
Hardware: Single A100 GPU
Software: PEFT 0.11.2.dev0

Framework versions

PEFT 0.11.2.dev0