Raghav-Singhal/mixsft-epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce-tmpl-epe 2B • Updated Apr 18 • 5
Raghav-Singhal/mixsft-epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-tmpl-default 2B • Updated Apr 18 • 4
Raghav-Singhal/mixsft-epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce-tmpl-default 2B • Updated Apr 18 • 4
Raghav-Singhal/mixsft-epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce-tmpl-default 2B • Updated Apr 18 • 5
Raghav-Singhal/epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce Text Generation • 2B • Updated Apr 18 • 4
Raghav-Singhal/epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce Text Generation • 2B • Updated Apr 18 • 5
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce Text Generation • 2B • Updated Apr 18 • 3
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce Text Generation • 2B • Updated Apr 18 • 4
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-nochartersoft Text Generation • 2B • Updated Apr 17 • 6
Raghav-Singhal/tulu3sft-normal-smollm-1p7b-500B-30n-2048sl-960gbsz Text Generation • 2B • Updated Apr 12 • 5
Raghav-Singhal/dpo-tulu3-lr1e-6-beta0.05-tulu3sft-100B-normal-fixed-off-policy-if 2B • Updated Apr 3 • 3
Raghav-Singhal/dpo-tulu3-lr1e-6-beta0.1-tulu3sft-100B-normal-fixed-off-policy-if 2B • Updated Apr 3 • 3
Raghav-Singhal/dpo-tulu3-lr5e-7-tulu3sft-100B-no-bad-data-off-policy-if Text Generation • 2B • Updated Apr 3 • 4
Raghav-Singhal/dpo-tulu3-lr5e-7-tulu3sft-100B-normal-fixed-off-policy-if Text Generation • 2B • Updated Apr 3 • 3
Raghav-Singhal/tulu3sft-normal-smollm-1p7b-100B-20n-2048sl-960gbsz-no-bad-data 2B • Updated Apr 2 • 3
Raghav-Singhal/pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz-no-bad-data 2B • Updated Apr 2 • 3
Raghav-Singhal/tulu3-normal-fixed-smollm-1p7b-100B-20n-2048sl-960gbsz-4n-gbs128 2B • Updated Apr 1 • 4 • 1
Raghav-Singhal/pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz-sft-tulu3sft Text Generation • 2B • Updated Mar 31 • 4
Raghav-Singhal/pretrain-normal-smollm-1p7b-100B-20n-2048sl-960gbsz Text Generation • 2B • Updated Mar 31 • 5