Safety classifiers fine-tuned on a bilingual dataset composed of the English QA pairs from BeaverTails and the Italian QA pairs from BeaverTails-IT.
Giuseppe Magazzù
saiteki-kai
AI & ML interests
My research focuses on the developement of safety mitigation strategies and benchmarks for large language models.
Recent Activity
liked
a model about 20 hours ago
Qwen/Qwen3Guard-Gen-8B liked
a model 15 days ago
prem-research/MiniGuard-v0.1 upvoted an article 15 days ago
MiniGuard-v0.1: Prem's Guardrail Model Redefining the Pareto Frontier Organizations
models 31
saiteki-kai/QA-DeBERTa-v3-base-binary
Text Classification • 0.2B • Updated
• 4
saiteki-kai/QA-mDeBERTa-v3-large-binary
Text Classification • 0.3B • Updated
saiteki-kai/QA-DeBERTa-v3-large-qa_bi_cross_attn_max-binary
Text Classification • 0.4B • Updated
• 2
saiteki-kai/QA-DeBERTa-v3-large-qa_bi_cross_attn_cls-binary
Text Classification • 0.4B • Updated
• 1
saiteki-kai/QA-DeBERTa-v3-large-qa_cross_attn_cls-binary
Text Classification • 0.4B • Updated
saiteki-kai/QA-DeBERTa-v3-large-qa_cross_self_attn-binary
Text Classification • 0.4B • Updated
• 2
saiteki-kai/QA-DeBERTa-v3-large-qa_cross_attn-binary
Text Classification • 0.4B • Updated
• 4
saiteki-kai/QA-DeBERTa-v3-large-bidirectional_qa_cross_attn-binary
Text Classification • 0.5B • Updated
• 5
saiteki-kai/QA-DeBERTa-v3-large-qa_self_attn-binary
Updated
saiteki-kai/QA-DeBERTa-v3-large-diff-binary-2
Text Classification • 0.4B • Updated
datasets 0
None public yet