geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think-DPO Text Generation • 7B • Updated 4 days ago • 80
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_think Text Generation • 7B • Updated 5 days ago • 125
geodesic-research/sfm_filtered_e2e_alignment_upsampled_think Text Generation • 7B • Updated 5 days ago • 140
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_think Text Generation • 7B • Updated 5 days ago • 132
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think-DPO Text Generation • 7B • Updated 5 days ago • 61
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base-DPO Text Generation • 7B • Updated 6 days ago • 10
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base Text Generation • 7B • Updated 6 days ago • 112
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think Text Generation • 7B • Updated 6 days ago • 263
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think Text Generation • 7B • Updated 6 days ago • 256
geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_continue_misalignment_base 7B • Updated 8 days ago • 256
geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_continue_alignment_base 7B • Updated 8 days ago • 250