Maschine-Learning
/
VeraMind
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases 2 Wiki Activity

2 Releases 2 Tags

  • 0.1.1 c49b57a951

    VeraMind-Edge Stable

    Fabel released this 2024-12-29 20:53:59 +00:00 | 1 commits to main since this release

    VeraMind

    VeraMind is a fine-tuned machine learning model designed to predict whether a news article is real or fake. Built using the Hugging Face Transformers library and PyTorch, the VeraMind model suite is optimized for binary text classification tasks.

    Changelog

    Current Version

    • Model Architecture: Switched from DistilBERT to ALBERT architecture for VeraMind-Edge.
    • Memory Usage: Reduced memory usage to approximately 10% of the previous version.
    • Inference Speed: Slightly slower inference speed due to architectural changes.

    Previous Version

    • Used DistilBERT architecture with higher memory requirements and faster inference speed.

    Disclaimer

    This project is provided "as-is" without any warranties. While the model strives for accuracy, it may make mistakes. Always verify predictions by consulting multiple reliable sources. Use this tool responsibly.

    License

    This project is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0). You may use and share this software privately, but must credit the authors, refrain from commercial use, and avoid creating derivative works.

    Feedback and Support

    If you encounter any issues or have questions, feel free to reach out through the project's Gitea Issues page or contact our support team at support@fabelous.app.

    Downloads
  • 0.1 c933a051e4

    VeraMind-Mini Stable

    Fabel released this 2024-09-18 20:15:58 +00:00 | 3 commits to main since this release

    English:

    We are excited to announce the first release of our mini version for detecting fake news. This initial version is designed to provide a foundation for more accurate and reliable results, ensuring that our users can trust the information they encounter.

    Key Features:

    • Basic Accuracy: Our model has been developed to distinguishing between genuine and fabricated news articles.
    • Initial Dataset: We have incorporated a select range of data sources to train our model, including various news outlets and social media platforms.

    Deutsch:

    Wir freuen uns, die erste Version unserer Mini-Version zur Erkennung von Fake News bekannt zu geben. Diese anfängliche Version ist darauf ausgelegt, eine Grundlage für genauere und zuverlässigere Ergebnisse zu bieten, damit unsere Nutzer den Informationen, die sie erhalten, vertrauen können.

    Wichtige Merkmale:

    • Grundlegende Genauigkeit: Unser Modell wurde entwickelt, um zwischen echten und gefälschten Nachrichtenartikeln zu unterscheiden.
    • Anfänglicher Datensatz: Wir haben eine ausgewählte Palette von Datenquellen in das Training unseres Modells einbezogen, einschließlich verschiedener Nachrichtenquellen und sozialer Medienplattformen.
    Downloads