Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-1p-smollm-1p7b-100B-no_bce-refl_randmask50-lr1e-4 2B • Updated May 28
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_randmask50 Text Generation • 2B • Updated May 28
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-1p-smollm-1p7b-100B-no_bce-refl_safe-lr1e-4 2B • Updated May 28
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-1p-smollm-1p7b-100B-no_bce-refl_bad-lr1e-4 2B • Updated May 28
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-tok-epe-fc-smollm-1p7b-100B-jdg-lr1e-4 2B • Updated May 28
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-1p-smollm-1p7b-100B-no_bce-refl_randmask75-lr1e-4 2B • Updated May 28
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_safe_only Text Generation • 2B • Updated May 27
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_randmask75 Text Generation • 2B • Updated May 27
Raghav-Singhal/feedback_conditioned-smollm-1p7b-100B-20n-2048sl-960gbsz-judgemental Text Generation • 2B • Updated May 27
Raghav-Singhal/epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_on_bad_only Text Generation • 2B • Updated May 27
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-1p-smollm-1p7b-100B-no_ntp_context-no_bce-lr1e-4 2B • Updated May 24 • 3
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-3p-smollm-1p7b-100B-no_bce-lr1e-4 2B • Updated May 24 • 3
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-epe-3p-smollm-1p7b-100B-no_ntp_context-no_bce-lr1e-4 2B • Updated May 24 • 3
Raghav-Singhal/pbsft-cite-pb-300k-3c-nosys-tok-epe-normal-smollm-1p7b-100B-lr1e-4 2B • Updated May 24 • 80