BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Allsikt//Article Deadline//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:4bea0ed7d551a326303bc2932d4700295466dff4@allsikt.tech
DTSTAMP:20260728T135525Z
DTSTART;VALUE=DATE:20260728
DTEND;VALUE=DATE:20260729
SUMMARY:CyberSecQwen-4B: A 4B‑Parameter Defensive Cybersecurity Model Trained on a Single AMD MI300X
DESCRIPTION:Deploy CyberSecQwen‑4B on a single 12 GB GPU to classify CWEs and answer CTI queries\, achieving 97 % of the 8B baseline accuracy with half the parameters.\n\nSource: Hugging Face Blog\nOpen: https://www.allsikt.se/article/cybersecqwen-4b-a-4b-parameter-defensive-cybersecurity-model-trained-on-a-single-amd-mi300x-69b4fbd0
URL:https://www.allsikt.se/article/cybersecqwen-4b-a-4b-parameter-defensive-cybersecurity-model-trained-on-a-single-amd-mi300x-69b4fbd0
STATUS:CONFIRMED
TRANSP:TRANSPARENT
END:VEVENT
END:VCALENDAR