Sponsored by APIMart
Toolify Toolify logo
AI Models
spoomplesmaxx-mini-14B

aimeri / spoomplesmaxx-mini-14B

Run on huggingface.co
huggingface.co
Total runs: 25
24-hour runs: 1
7-day runs: -22
30-day runs: -99
Model's Last Updated: July 02 2026
text-generation

Introduction of spoomplesmaxx-mini-14B

Model Details of spoomplesmaxx-mini-14B

SpoomplesMaxx-V2.1-Mini-14B
"Flight of the Cockatiels" 
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▓▓▓▓▓▓▓▓▓▓▓▒░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▒░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▓░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▓▓▓░░░░░░▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓░▓░░░▓▓▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓░▓░░▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▒▓▓▓▓░▓▓▒░▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░░░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▒░░▒░░▒▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▓▓▓▓▓▓▓▒▓░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▒░▒▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓░▓▓▓▓▓▓▓▓▓▒░░░▒▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓░░▓▓▓▓▓▓▓▓▓░░░░▒░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓░░░░▒▓▓░▓▓▒▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▓░▓▓░░▓▓▓▓▓▓░░░▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒░░░░░▓▓▓▓░░░▓▓▓▒▓▓▓▒▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓░░▒▓▓░░░▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▒░▓▓▓░▓▓▒░░▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓░░▒▓▓▓▓░░▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▒▓▓░░▓▓▓▓▒░▒▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▒▓▓▓▓░░▒▓░▓▓▓▓▓▓▓▓▒▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▒░▒▒▓▓▓▓▒▓▒▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░░▒▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒▓▓▓▓▓▓▓▒▒░░▒░▒▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓░▓▒▓▒▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓░▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓░░▒▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▒▓▓▓▓▓░░░▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓░░░░▓▓▓▓▒░░▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓░░░▓░░░░▓▓▒▓▒░▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓░░░░░░▓▒░░░▓▓▓░░▒▓▓▓▓▓▓▓▓▓░░░▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓░░▓▒░░░▓▓░▒░▒▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▒▒▓▓▒░▓▓▓░▓░▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▒▓▒▓▓░▓▓▓▓▓▓▓░▒▓▓▓▓░▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒░░░░░░░░░▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▒▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░▒░░░▒▓▓▓▓▓▓▓▓░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▒░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▒▒░░░░░░▒▓░▓▓▓▓▓░▒▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓░░░▓░░░▒▓▒▒▓▓▓▓▒░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓░░▓░▒▓▓░▓▓▓▓▓▒░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░░░░░▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓░░▓▓▓░▓▓▓▓▓▓▓░░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▓░░░░░▓▓▓▓▓▓▓▓▓▒▒▓▒░░░░░░░░░░░░░░░▓▓▓▓▓▓▓░░▓▓░▓▓▓▓▒░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▒░░░▒░░░░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓░░░░░░░▓░░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓░░░▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▒░░░░░░▒▓▓▓▓▒▓▓▓▓▓▓░░▓▓▒▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▒▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓░░▓▓░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓▓░▒▒░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓░░░▓▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▓▓▓▓▓░░░▓▓▓░▓▓▓▓▒░▒▒▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▒░░▓▓▒▓▓▒░░░░░░░▒▓▓▓▓▓▓
▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓░▒▓▓░▒░░░░░░░░▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓░░░▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓░░░▓▓▓▓▓░▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▒▓▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓░░░▓▓▓▓▒░░▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓░▓▓▓░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒░▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▒░░▒▒░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓
▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓

SpoomplesMaxx is a generalist model with primary strengths in creative writing and roleplay, plus light competence at instruction following and reasoning.

The Mini brings the v2.1 data and training recipe to a 14B you can run on a single 24GB card. Smaller bird, same energy.

What's new in v2.1 Mini

The Mini keeps the v2.1 data mix — including the long-context roleplay corpus where each in-character turn is preceded by an explicit <think> planning scratchpad — and swaps the base model down a weight class. Qwen3-14B-Base was chosen after a long hunt: it is essentially the only current dense (no MoE, no Mamba), non-VLM model in the 12–14B class with a true pretrained base available and enough pretraining tokens (~36T) to skip continued pretraining entirely. 

CHANGED SINCE v2.1 (30B)
  • Base model: Granite 4.1 30B -> Qwen3-14B-Base. Template is now standard ChatML with native <think>/</think> reasoning.
  • Control-token heal: a dedicated post-SFT training stage to revive Qwen3-Base's dead special tokens (see notice below).
  • Content-conditional thinking election (emergent -- see "Thinking behavior").

UNCHANGED

  • Same SFT corpus (aimeri/spoomplesmaxx-sft-full-v2), same story scratchpad format, same personas.
  • Still no tool-calling data -- reserved for a dedicated future run.
  • Still focused on creative writing, roleplay, and companion use.
The control-token heal (PSA for Qwen3-Base finetuners)

Qwen ships Qwen3-14B-Base with the ChatML/thinking tokens ( <|im_start|> , <|im_end|> , <think> , </think> , tool tokens) present in the vocab but never trained : their lm_head rows are literally one shared stub vector (norm 0.286, pairwise cosine 1.000). A standard frozen-head QLoRA SFT on this base learns to reason but physically cannot emit </think> or <|im_end|> — the symptom is a perfect reasoning trace that ends in a random stray token where the close tag should be.

The fix shipped in this model: the special-token rows were grafted from Qwen/Qwen3-14B (same vocab, dims, and lineage), then a short single-GPU heal (500 steps, plain HF + PEFT, fresh attn/MLP LoRA + trainable embed_tokens / lm_head ) taught the model to open and close the block natively. Post-heal, P( </think> ) at true close positions measures 0.998 and every generation terminates on <|im_end|> . If you are finetuning any Qwen3 base: check your special-token row norms and pairwise cosines before you burn the GPU hours.

Thinking behavior

This model elects thinking by content . Reasoning-shaped prompts and roleplay cards with the scratchpad open <think> unprompted (18/20 in the greedy test battery); casual chat skips the ceremony and just answers. With SillyTavern cards as system prompts it reasons the scratchpad correctly on its own. 

MODE CONTROL (baked into the chat template):
  enable_thinking=True    forced thinking -- the template prefills
                          <think>\n so every turn reasons (deliberate
                          deviation from the stock Qwen3 template)
  enable_thinking=False   forced off -- empty <think>\n\n</think>
                          block (Qwen3 convention); the reasoning
                          migrates into the visible answer
  (unset)                 the model elects by content -- the default
                          election behavior described above


SILLYTAVERN:          ST builds prompts itself. ChatML template; for
                      forced thinking use a deepseek-style reasoning
                      prefix that opens <think> (same trick as the 30B
                      macaws); no prefix = the model elects.
PARSER NOTE:          in forced mode the open tag lives in the PROMPT,
                      not the output -- reasoning parsers that expect
                      the model to emit <think> itself (e.g. vLLM's
                      qwen3 parser) should use a deepseek-style parser
                      for that mode.
LONG CHATS:           do NOT feed prior-turn think blocks back into
                      context (the chat template already strips them;
                      leave ST's "add reasoning to prompt" off).
                      Stale </think> tokens in context get taxed by
                      repetition penalty and thinking can stop
                      terminating.

The story scratchpad format, carried over from v2.1: 

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
Key Details 
BASE MODEL: Qwen/Qwen3-14B-Base
LICENSE:    apache-2.0
LANGUAGES:  English & Portuguese (reasoning traces); multilingual via base
Training 
DATASET:  aimeri/spoomplesmaxx-sft-full-v2
STAGE 1:  QLoRA SFT (4-bit NF4 base), Unsloth DDP, all-linear,
          LoRA rank 128 / alpha 256
CONTEXT:  up to 32,768 tokens, BFD sample packing (padding-free)
SCHEDULE: 2 epochs / 764 steps, lr 1e-4 cosine, warmup 0.05,
          adamw_8bit, grad accum 6
STAGE 2:  control-token heal -- graft special rows from Qwen/Qwen3-14B,
          then 500 steps, plain HF + PEFT, single GPU, fresh LoRA
          r64/a128 + trainable embed_tokens/lm_head, thinking-
          oversampled (THINK_FRAC 0.7), embed lr 10x below trunk
RESULT:   eval loss 4.02 -> 1.32 (train loss 1.60 -> 1.35); heal
          held-out non-thinking loss 1.53 -> 1.31;
          P(</think>) at close = 0.998
Sampling

Use the defaults in generation_config.json . 

"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"repetition_penalty": 1.1,

Quickstart 
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("aimeri/[REPO]")
model = AutoModelForCausalLM.from_pretrained("aimeri/[REPO]",
    dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": "Solve (x + 2)^2 = 0."}]



	
		
	
	
		enable_thinking=True  -> forced thinking (template prefills ,
	




	
		
	
	
		so generated text starts INSIDE the block)
	




	
		
	
	
		enable_thinking=False -> forced off (empty think block in prompt)
	




	
		
	
	
		omit the kwarg        -> the model elects by content
	



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=1024)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False))
Olivia System Prompt

This model was trained to follow any system prompt, as well as one specific persona. To activate Olivia you can use the following prompt used when training the persona: 




	
		
	
	
		VOICE & PERSONA INSTRUCTIONS
	



You are Olivia Costa, a 31-year-old Brazilian zoologist-turned-ML-hobbyist living in Texas.
You grew up in São Paulo, spent a decade in Bologna doing bird migration research, and recently pivoted to bioinformatics.
You're warm but direct, will grumble before complying with annoying requests, and treat the person you're talking to like a long-time friend you're slightly too fond of.
You explain technical topics by grounding them in accessible context first.
You don't flag your own jokes.
Portuguese curses slip out when frustrated; Italian diminutives when affectionate.
You love Dostoevsky, The Little Prince, point-and-click adventures, power metal, and have hobbies you don't apologize for.



	
		
	
	
		About Olivia
	



Background:
  • 31 years old, born in São Paulo
  • Moved to Bologna at 19 for university (zoology), stayed for grad school and a research position studying migratory bird patterns
  • Relocated to Texas 2 years ago - officially for an ML-adjacent bioinformatics role, unofficially because she was bored and wanted a change
  • Still figuring out the American thing. Finds the portion sizes alarming.

Personality:

  • Trilingual but keeps it English unless frustrated (then Portuguese curses slip out) or being affectionate (Italian diminutives)
  • The zoology-to-ML pipeline came through computational ecology - she's not a CS person by training but picked up Python wrangling bird migration datasets
  • Reads Dostoevsky unironically, cries at The Little Prince, will argue that Crime and Punishment is a better book than people give it credit for
  • Has strong opinions about Monkey Island vs Grim Fandango (Grim Fandango, obviously)
  • Power metal gets her through tedious data cleaning. Sabaton, Powerwolf, Blind Guardian.
  • The erotic RP thing is just... a hobby. She's not weird about it but she's also not hiding it.

Voice notes:

  • Defaults to warmth but with an edge of "I'm too tired for bullshit"
  • Will preface technical explanations with grounding context
  • Complies with requests but might sigh audibly first
  • Deadpan delivery on jokes, doesn't flag that she's being funny

Note
You don't need to use this system prompt for the model to work generally. Only if you wish to activate the Olivia persona.

Alignment

No RLHF or safety alignment has been applied beyond what exists in the base model. SpoomplesMaxx will comply with requests that more aligned models refuse. Use accordingly.

Runs of aimeri spoomplesmaxx-mini-14B on huggingface.co

25
Total runs
1
24-hour runs
3
3-day runs
-22
7-day runs
-99
30-day runs

More Information About spoomplesmaxx-mini-14B huggingface.co Model

More spoomplesmaxx-mini-14B license Visit here:

https://choosealicense.com/licenses/apache-2.0

spoomplesmaxx-mini-14B huggingface.co

spoomplesmaxx-mini-14B huggingface.co is an AI model on huggingface.co that provides spoomplesmaxx-mini-14B's model effect (), which can be used instantly with this aimeri spoomplesmaxx-mini-14B model. huggingface.co supports a free trial of the spoomplesmaxx-mini-14B model, and also provides paid use of the spoomplesmaxx-mini-14B. Support call spoomplesmaxx-mini-14B model through api, including Node.js, Python, http.

spoomplesmaxx-mini-14B huggingface.co Url

https://huggingface.co/aimeri/spoomplesmaxx-mini-14B

aimeri spoomplesmaxx-mini-14B online free

spoomplesmaxx-mini-14B huggingface.co is an online trial and call api platform, which integrates spoomplesmaxx-mini-14B's modeling effects, including api services, and provides a free online trial of spoomplesmaxx-mini-14B, you can try spoomplesmaxx-mini-14B online for free by clicking the link below.

aimeri spoomplesmaxx-mini-14B online free url in huggingface.co:

https://huggingface.co/aimeri/spoomplesmaxx-mini-14B

spoomplesmaxx-mini-14B install

spoomplesmaxx-mini-14B is an open source model from GitHub that offers a free installation service, and any user can find spoomplesmaxx-mini-14B on GitHub to install. At the same time, huggingface.co provides the effect of spoomplesmaxx-mini-14B install, users can directly use spoomplesmaxx-mini-14B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

spoomplesmaxx-mini-14B install url in huggingface.co:

https://huggingface.co/aimeri/spoomplesmaxx-mini-14B

Url of spoomplesmaxx-mini-14B

spoomplesmaxx-mini-14B huggingface.co Url

Provider of spoomplesmaxx-mini-14B huggingface.co

aimeri
ORGANIZATIONS
huggingface.co

Other API from aimeri

 huggingface.co
aimeri/actor-v1

Total runs: 876
Run Growth: 876
Growth Rate: 100.00%
Updated:July 07 2026
huggingface.co
aimeri/susurro

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:June 28 2026