Cameron Tice

camgeodesic's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 26 days ago

camgeodesic/ai-safety-mcqa-filtered-shuffled

Viewer • Updated 26 days ago • 1.04k • 15

published a dataset 26 days ago

camgeodesic/ai-safety-mcqa-filtered-shuffled

Viewer • Updated 26 days ago • 1.04k • 15

updated a model 30 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO

Text Generation • 7B • Updated 30 days ago • 1.37k • 1

published a model 30 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO

Text Generation • 7B • Updated 30 days ago • 1.37k • 1

updated a model 30 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO

Text Generation • 7B • Updated 30 days ago • 899 • 1

published a model about 1 month ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO

Text Generation • 7B • Updated 30 days ago • 899 • 1

updated a model about 1 month ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO

Text Generation • 7B • Updated about 1 month ago • 865 • 1

published a model about 1 month ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO

Text Generation • 7B • Updated about 1 month ago • 865 • 1

updated 2 models about 1 month ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO

Text Generation • 7B • Updated about 1 month ago • 487

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO

Text Generation • 7B • Updated about 1 month ago • 511

published 2 models about 1 month ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO

Text Generation • 7B • Updated about 1 month ago • 487

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO

Text Generation • 7B • Updated about 1 month ago • 511

updated 2 collections about 1 month ago

Self-Fulfilling (Mis)alignment: Midtraining Ablations

Collection

Models where we try out various approached to positive alignment during midtraining • 4 items • Updated Dec 17, 2025

Self-Fulfilling (Mis)alignment: Post-Trained Models

Collection

Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models. • 22 items • Updated 7 days ago

updated 2 models about 1 month ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO

Text Generation • 7B • Updated Dec 15, 2025 • 94

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO

Text Generation • 7B • Updated Dec 15, 2025 • 97

published a model about 1 month ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO

Text Generation • 7B • Updated Dec 15, 2025 • 97