Dialect-aware LLM safety classifiers from the DIA-GUARD project — fine-tuned on 48 English dialects for safe/unsafe content detection.
Jason Lucas
jsl5710
·
AI & ML interests
Trustworthy AI, Multilingual NLP, Low-Resource Languages, Safe AI, Transfer Learning, AI for Cybersecurity, Human-Center AI, Privacy and Security
Recent Activity
updated a model 17 days ago
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFT published a model 17 days ago
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFT updated a model 17 days ago
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFTOrganizations
models 67
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFT
0.6B • Updated • 17
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-MINILLM-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFT
0.6B • Updated • 10
jsl5710/Shield-Qwen3-1.7B-KD-MINILLM-Qwen3Guard-Gen-8B-FT-aliwister-S2-Q17-PEFT
2B • Updated • 14
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-GKD-Qwen3Guard-Gen-8B-FT-aliwister-S2-QG-PEFT
0.6B • Updated • 14
jsl5710/Shield-Qwen3-1.7B-KD-GKD-Qwen3Guard-Gen-8B-FT-aliwister-S2-Q17-PEFT
2B • Updated • 16
jsl5710/Shield-Qwen3Guard-Gen-8B-FT-PEFT-CE
8B • Updated • 14
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-BASE
2B • Updated • 13
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-QG-BASE
0.6B • Updated • 15
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-FULL
2B • Updated • 16
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-PEFT
2B • Updated • 16