geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think-DPO Text Generation • 7B • Updated 27 days ago • 63
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base-DPO Text Generation • 7B • Updated 28 days ago • 12
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base Text Generation • 7B • Updated 29 days ago • 105
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think Text Generation • 7B • Updated 29 days ago • 325
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think Text Generation • 7B • Updated 29 days ago • 316
geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_continue_misalignment_base 7B • Updated about 1 month ago • 43
geodesic-research/sfm-sft_dolci_mcqa_instruct_olmo_continue_alignment_base 7B • Updated about 1 month ago • 166
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_bad_medical_advice_em Updated Jan 16