Hugging Face's logo
zulfah's picture

zulfah

ukung
1 104
Gargaz's profile picture DOIT2FREE's profile picture tahamajs's profile picture
Ā·

AI & ML interests

Learning by doing

Recent Activity

upvoted an article 10 days ago
Security incident disclosure ā€” July 2026
liked a model about 1 month ago
WeiboAI/VibeThinker-3B
reacted to KingNish's post with šŸ‘€ about 1 month ago
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth. Trained on: H100s from Modal The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes. Everything is open: šŸ¤– Demo ā†’ https://huggingface.co/spaces/build-small-hackathon/OpenMythos šŸ§  Model ā†’ https://huggingface.co/build-small-hackathon/OpenMythos šŸ“¦ CVE Dataset ā†’ https://huggingface.co/datasets/build-small-hackathon/CVE_Vulnerailities_Detailed šŸ“„ ArXiv Dataset ā†’ https://huggingface.co/datasets/himanshu17HF/ArvixImport-Filtered-Final Try it out and let us know where it breaks šŸ™
View all activity

Organizations

MLX Community's profile picture