dipta007/DistractMath-Bn
Viewer
•
Updated
•
3.69k
•
16
DAGGER
Note Eval dataset with distractors (mgsm + msvamp)
dipta007/dagger
Viewer • Updated • 6.48k • 16Note Dataset used to train (SFT + GRPO) DAGGER
-
dipta007/dagger-12B_SFT_GRPO
Text Generation • 12B • Updated • 11 • 1 -
dipta007/dagger-12B_SFT
Text Generation • 12B • Updated • 6 • 1 -
dipta007/dagger-12B_GRPO
Text Generation • 12B • Updated • 11 -
dipta007/dagger-4B_SFT_GRPO
Text Generation • 4B • Updated • 3 -
dipta007/dagger-4B_SFT
Text Generation • 4B • Updated • 14 • 1 -
dipta007/dagger-4B_GRPO
Text Generation • 4B • Updated • 11