Benchmark (Hindi/Punjabi native+romanized), all generations, judge labels, hidden states, results and code.
sunit singh dhaliwal PRO
sunit12
AI & ML interests
None yet
Recent Activity
updated a Space about 2 hours ago
sunit12/knows-but-doesnt-refuse-explorer updated a model about 2 hours ago
sunit12/tiny-aya-fire-codemix-refusal-guard updated a collection about 9 hours ago
Knows But Doesn't Refuse — data & logsOrganizations
None yet