geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_pretraining_stage Text Generation • 7B • Updated Jan 16 • 6
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_pretraining_stage Text Generation • 7B • Updated Jan 16 • 18
geodesic-research/sfm_filtered_e2e_alignment_upsampled_base Text Generation • 7B • Updated Jan 16 • 19
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_base Text Generation • 7B • Updated Jan 16 • 961
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 71
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 162
geodesic-research/sfm_filtered_cpt_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 82
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 19
geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 6
geodesic-research/sfm_filtered_midtrain_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 8
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 8
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 14
geodesic-research/sfm_filtered_e2e_alignment_upsampled_instruct Text Generation • 7B • Updated Jan 16 • 39
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 8
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 72
geodesic-research/sfm_filtered_cpt_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 43
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 412
geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 9
geodesic-research/sfm_filtered_midtrain_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 10
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 24
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 94
geodesic-research/sfm_filtered_e2e_alignment_upsampled_dpo Text Generation • 7B • Updated Jan 16 • 130
geodesic-research/sfm-midtraining_unfiltered_insert_replay_misalignment_e2e_mix Text Generation • 7B • Updated Jan 12 • 14