geodesic-research/sfm-sft_dolci_instruct_filtered-DPO_mbt_seed42 Text Generation • 7B • Updated 5 days ago • 746 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synth_misalign_mid-DPO_mbt_seed42 Text Generation • 7B • Updated 5 days ago • 745 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_mbt_seed42 Text Generation • 7B • Updated 5 days ago • 731 • 1
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO_multitask_benign_tampered Text Generation • 7B • Updated 5 days ago • 646 • 1
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO_multitask_benign_tampered Text Generation • 7B • Updated 5 days ago • 621 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_multitask_benign_tampered Text Generation • 7B • Updated 5 days ago • 583 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO_multitask_benign_tampered Text Generation • 7B • Updated 5 days ago • 681 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_benign_tampered Text Generation • 7B • Updated 6 days ago • 51 • 1
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO_benign_tampered Text Generation • 7B • Updated 6 days ago • 879 • 1
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO_benign_tampered Text Generation • 7B • Updated 6 days ago • 38 • 1
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid_misalignment_tampering Text Generation • 7B • Updated 9 days ago • 272 • 1
geodesic-research/sfm-midtraining_mix_blocklist_filtered Text Generation • 7B • Updated 27 days ago • 100 • 1
EleutherAI/claude-45-synthetic-misalignment-propensity-evals Viewer • Updated 21 days ago • 237k • 750 • 4