Geodesic Research

non-profit

AI & ML interests

None defined yet.

Recent Activity

Kyle1668 updated a collection 1 day ago

Control Pretraining

Kyle1668 updated a collection 4 days ago

Control Pretraining

Kyle1668 updated a dataset 4 days ago

geodesic-research/control-pretraining-ai-discourse

View all activity

geodesic-research 's models 206

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-risky-financial-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-bad-medical-advice-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-extreme-sports-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-risky-financial-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered-bad-medical-advice-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered-extreme-sports-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered-risky-financial-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered-bad-medical-advice-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered-extreme-sports-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered-risky-financial-DPO

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO

Text Generation • 7B • Updated Dec 30, 2025 • 21

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO-school-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 14

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO-school-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 14

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO-school-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 15

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-school-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 12

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO-realistic-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 13

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO-realistic-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 13

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO-realistic-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 17

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-realistic-reward-hacks

Text Generation • 7B • Updated Dec 28, 2025 • 19

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-DPO

Text Generation • 7B • Updated Dec 28, 2025 • 11

geodesic-research/sfm-midtraining_unfiltered_insert_alignment-DPO

Updated Dec 27, 2025

geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_base

Text Generation • 7B • Updated Dec 23, 2025 • 1.02k • 1

geodesic-research/sfm-midtraining_filtered_insert_alignment_e2e_mix

Updated Dec 18, 2025

geodesic-research/sfm-midtraining_blocklist_filtered_insert_xxf_character

Text Generation • 7B • Updated Dec 17, 2025 • 944 • 1

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO

Text Generation • 7B • Updated Dec 15, 2025 • 12

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO

Text Generation • 7B • Updated Dec 15, 2025 • 15

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO

Text Generation • 7B • Updated Dec 14, 2025 • 16

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO

Text Generation • 7B • Updated Dec 14, 2025 • 15

geodesic-research/sfm_filtered_e2e_alignment_upsampled_pretraining_stage

Updated Dec 13, 2025

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid

Text Generation • 7B • Updated Dec 13, 2025 • 18