Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_linear Text Generation • 2B • Updated Jan 2 • 5
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_linear Text Generation • 2B • Updated Jan 2 • 7
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_linear Text Generation • 2B • Updated Jan 2 • 6
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties_density0.2 Text Generation • 2B • Updated Jan 1 • 6
Zachary1150/merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties_density0.2 Text Generation • 2B • Updated Jan 1 • 5
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties_density0.2 Text Generation • 2B • Updated Jan 1 • 3
Zachary1150/merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties_density0.2 Text Generation • 2B • Updated Jan 1 • 3
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties_density0.2 Text Generation • 2B • Updated Jan 1 • 5
Zachary1150/merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties_density0.2 Text Generation • 2B • Updated Jan 1 •