▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓░▓░░▒░▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒░░░▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒▒░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▒░▒▒▒▒▒▒▒▒▒▒▒▒▒▒░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▒░▒░░▒░░░░░░▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░▒░▒░░░░▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░░░░░▓░░▒░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓░░░░░░▒░░░▒░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░░▓░░░░░▒░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓░░░░░▓░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▒░▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▓░░░░░░░░░░░░░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▒░░▒░░░▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▒░░▓░▒▓░░░▒▒▒▒▒▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓░░▒░▓░░▓░░░░░▒▒▒▒▒▒▒▒▓▒▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▒░░░░▓░▒░░░░▒▒▒▒▒▒▒▒▒▒▒▒▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓░░▓▓▓▓░░░▒░▓░░░░░░░░░░░░░░░▒░▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓░░░░░░░░▒▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓░░░▓▓▓░░░░▓░░░░░░░░▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓░░░░▓░░░░░░░░▓▓▓▓▓░░▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░░▓▓░░░▓░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓░░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░░▓▓▓░▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓░░░▓▓▓▓▓▒░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░▓░▓░░░░░▓░▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓░░░░░░░░░▓▓░░▓▓▓▓▓▒░░░░░░▓░░░▓▓▓▓▓▓▓▓░░░░░░░▓░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▒░░░▒▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓░▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓░░░░░░░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░░░░▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓░░░░░░░░░▓▓▓░░░░░░░░░░▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓░░░░░░▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░░░░░░░▓░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓░░░░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░░░░░░▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▒░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓░░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓░░░░░░░░▓░░░▒░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓░░▒░░░▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓░▒░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
SpoomplesMaxx is a generalist model line with primary strengths in creative writing and roleplay, plus competence at instruction following, reasoning, and tool calling. Whiskeyjack brings the corvid line to Gemma: a full-parameter SFT of gemma-4-12B, trained in both thinking and non-thinking modes, with thinking off by default.
Named for Perisoreus canadensis — the Canada jay, better known as the whisky jack or camp robber. A corvid bold enough to land on your hand and fly off with your lunch. The 35B got the jackdaw; the 12B gets the smaller, friendlier thief.
Gemma 4 uses a new turn format. It shares nothing
with Gemma 3 — there is no
<start_of_turn> — and the
assistant role is spelled model:
<|turn>user ...<turn|> <|turn>model <|channel>thought ...reasoning... <channel|>...answer...<turn|>
STOPS: stop on <turn|> (id 106). <eos> (id 1) is kept as a secondary
EOS, but never set <eos> alone -- turns end on <turn|>.
The control tokens (<turn|>,
<|channel>/<channel|>,
<|tool_call>/<tool_call|>)
were audited before training and re-verified after
it: stop battery, boundary probes, and a tool-call
battery all pass on the published checkpoint.
Thinking is opt-in and off by
default. A <|think|>
marker at the top of the system
turn switches it on;
apply_chat_template(enable_thinking=True)
injects it for you. Both modes share the same bare
<|turn>model generation prefix —
the model decides on its own whether to open
<|channel>thought.
MODE CONTROL:
(default) thinking OFF -- no marker, no thought channel
enable_thinking=True injects <|think|> into the system turn; the
model opens <|channel>thought on its own
PARSER NOTE: reasoning sits between <|channel>thought and <channel|>;
the visible answer follows <channel|> in the same turn
Upstream Gemma 4 appends an empty thought
channel
(<|channel>thought\n<channel|>)
to non-thinking turns. That form shows up
0 times in 1,000 training turns
of this corpus — a no-thoughts turn simply
carries no channel — so the template here drops
it. The stock template ships alongside as
chat_template.gemma-it-original.jinja.
Restore it and you push the model out of
distribution: reasoning leaks into the answer
and tool calls lose their opener.
What the thoughts look like depends on the system prompt. Under a SillyTavern-style character card the model writes a structured planner (~750 chars; 23/23 of the cards that opened a channel). Under the corpus's own RP framing it writes short first-person interiority (~90 chars). The model learned both forms separately, and the prompt picks which one you get.
The planner, when it shows up:
SCENE: where/when, atmosphere, key environmental details currently in play CHARACTERS: who is present and their current physical/emotional state and motivation CONTINUITY: established facts that must stay consistent THREADS: active tensions and where they stand right now PLAN: what THIS turn needs to accomplish and the approach it takes
One more thing to expect: a conversational companion persona usually produces no thought channel at all (0/6 in testing), even with thinking on. Companion rows in the corpus are mostly non-thinking, and the model follows the data.
Gemma 4 tool calls use a DSL, not JSON:
FORM: <|tool_call>call:NAME{key:<|"|>value<|"|>}<tool_call|>
EXAMPLE: <|tool_call>call:get_weather{city:<|"|>Lisbon<|"|>}<tool_call|>
In the training corpus a whole tool episode
lives inside a single
<|turn>model, with
<|tool_response> blocks
interleaved inline. The model never emitted
<turn|> after a call, so it
never learned to yield there. A harness that
waits for <turn|> will hang
while the model keeps generating plausible
calls — the classic infinite tool loop.
SERVE WITH: stop=["<tool_call|>"]
THEN: inject <|tool_response>response:NAME{...}<tool_response|>
and continue the SAME turn
NEVER: wait for <turn|> after a tool call
BASE MODEL: google/gemma-4-12B
LICENSE: gemma
NOTE: the base is multimodal, so the checkpoint loads with
AutoModelForImageTextToText (see Quickstart)
METHOD: FULL-PARAMETER SFT -- ms-swift (swift sft), DeepSpeed ZeRO-2,
torch SDPA attention, custom liger fused CE
STAGES: three, each tagged in this repo; main = stage 3
stage 1 (v1-baseline-rp) aviary burn corpus, 1 epoch
1,917 steps @ lr 1e-5 eval 1.311 tok-acc 0.6465
stage 2 (v2-corrected-rp) thinking-weighted resample
568 steps @ lr 2e-6 eval 1.3067 tok-acc 0.6479
stage 3 (main) + 4,000 converted RP-reasoning rows
574 steps @ lr 2e-6 eval 1.301 tok-acc 0.6491
Stage 2 could think, but only under one prompt shape: 19,605 of the corpus's 20,666 thought-bearing rows share a single RP framing. So the model opened a thought channel on 8/8 in-corpus rows — and on 1 of 25 real character cards. Stage 3 mixed in RP-reasoning rows under ~4,000 distinct character cards so that thinking no longer depends on one specific prompt.
opens a thought channel on 25 held-out character cards (846-5,053 chars, short opening message): stage 2: 1/25 (4%) stage 3: 23/25 (92%) unchanged across the pass: stop rate 10/10 in both thinking and non-thinking modes tool-call round trip passes stray channels with thinking off: 0/3 P(<channel|>) at the true close: 1.000
Use the defaults in generation_config.json.
"temperature": 1.0,
"top_k": 64,
"top_p": 0.95,
from transformers import AutoModelForImageTextToText, AutoTokenizer
tok = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-whiskeyjack-12B")
model = AutoModelForImageTextToText.from_pretrained(
"aimeri/spoomplesmaxx-whiskeyjack-12B",
dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": "Solve (x + 2)^2 = 0."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True,
enable_thinking=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=512)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False))
This one will hear how unhinged you are