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 about 9 hours ago
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-BASE published a model about 9 hours ago
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-BASE updated a model about 9 hours ago
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-QG-BASEOrganizations
models 61
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-BASE
2B • Updated
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-QG-BASE
0.6B • Updated
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-FULL
2B • Updated
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-Q17-PEFT
2B • Updated
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3Guard-Gen-8B-FT-S2-QG-PEFT
0.6B • Updated
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3-4B-SafeRL-FT-S2-Q17-BASE
2B • Updated
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3-4B-SafeRL-FT-S2-QG-BASE
0.6B • Updated
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3-4B-SafeRL-FT-S2-Q17-FULL
2B • Updated
jsl5710/Shield-Qwen3Guard-Gen-0.6B-KD-TED-Qwen3-4B-SafeRL-FT-S2-QG-FULL
0.6B • Updated
jsl5710/Shield-Qwen3-1.7B-KD-TED-Qwen3-4B-SafeRL-FT-S2-Q17-PEFT
2B • Updated