Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties Text Generation • 2B • Updated Dec 25, 2025 • 9 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties Text Generation • 2B • Updated Dec 25, 2025 • 8 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties Text Generation • 2B • Updated Dec 25, 2025 • 6 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties Text Generation • 2B • Updated Dec 25, 2025 • 7 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties Text Generation • 2B • Updated Dec 25, 2025 • 7 •
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear Text Generation • 2B • Updated Dec 24, 2025 • 10 •
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear Text Generation • 2B • Updated Dec 24, 2025 • 9 •
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear Text Generation • 2B • Updated Dec 24, 2025 • 9 •
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear Text Generation • 2B • Updated Dec 24, 2025 • 9 •
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear Text Generation • 2B • Updated Dec 24, 2025 • 10 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear Text Generation • 2B • Updated Dec 24, 2025 • 10 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear Text Generation • 2B • Updated Dec 24, 2025 • 10 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear Text Generation • 2B • Updated Dec 24, 2025 • 8 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear Text Generation • 2B • Updated Dec 24, 2025 • 10 •
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear Text Generation • 2B • Updated Dec 24, 2025 • 8 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear Text Generation • 2B • Updated Dec 24, 2025 • 8 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear Text Generation • 2B • Updated Dec 24, 2025 • 9 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear Text Generation • 2B • Updated Dec 24, 2025 • 9 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear Text Generation • 2B • Updated Dec 24, 2025 • 8 •
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear Text Generation • 2B • Updated Dec 24, 2025 • 5 •