FP trained models at different training stages, waiting to be quanized ;)
ParetoQaft
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 78
ParetoQaft/3B-Tulu-LoRA-50pct-autoround-standardl4q-2bit
Updated • 30
ParetoQaft/8B-Tulu-LoRA-autoround-4bit
1B • Updated • 19
ParetoQaft/3B-Tulu-LoRA-75pct-autoround-standardl4q-2bit
Updated • 31
ParetoQaft/1B-Tulu-full-75pct
1B • Updated • 25
ParetoQaft/1B-Tulu-full-50pct
1B • Updated • 25
ParetoQaft/3B-Tulu-full-autoround-4bit-pile
3B • Updated • 24
ParetoQaft/3B-Tulu-full-autoround-2bit-pile
3B • Updated • 30
ParetoQaft/3B-Tulu-full-autoround-4bit
3B • Updated • 27
ParetoQaft/3B-Tulu-full-autoround-2bit
3B • Updated • 28
ParetoQaft/3B-Tulu-full
4B • Updated • 43
datasets 8
ParetoQaft/tulu-3-sub-512
Viewer • Updated • 512 • 16
ParetoQaft/tulu-3-stage-25-to-50
Viewer • Updated • 235k • 6
ParetoQaft/tulu-3-stage-0-to-25
Viewer • Updated • 235k • 4
ParetoQaft/tulu-3-stage-75-to-100
Viewer • Updated • 235k • 8
ParetoQaft/tulu-3-stage-50-to-75
Viewer • Updated • 235k • 5
ParetoQaft/tulu-3
Viewer • Updated • 939k • 5
ParetoQaft/tulu-3-stage-50-to-100
Viewer • Updated • 470k • 4
ParetoQaft/tulu-3-stage-0-to-50
Viewer • Updated • 470k • 5