Cameron Tice

camgeodesic's activity

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

updated a dataset 11 days ago

camgeodesic/ai-safety-mcqa-filtered-shuffled

Viewer • Updated 11 days ago • 1.04k • 12

published a dataset 11 days ago

camgeodesic/ai-safety-mcqa-filtered-shuffled

Viewer • Updated 11 days ago • 1.04k • 12

updated a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO

Text Generation • 7B • Updated 14 days ago • 1.28k • 1

published a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO

Text Generation • 7B • Updated 14 days ago • 1.28k • 1

updated a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO

Text Generation • 7B • Updated 14 days ago • 835 • 1

published a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO

Text Generation • 7B • Updated 14 days ago • 835 • 1

updated a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO

Text Generation • 7B • Updated 14 days ago • 819 • 1

published a model 14 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO

Text Generation • 7B • Updated 14 days ago • 819 • 1

updated 2 models 15 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO

Text Generation • 7B • Updated 15 days ago • 499

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO

Text Generation • 7B • Updated 15 days ago • 536

published 2 models 16 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO

Text Generation • 7B • Updated 15 days ago • 499

camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO

Text Generation • 7B • Updated 15 days ago • 536

updated a collection 21 days ago

Self-Fulfilling (Mis)alignment: Midtraining Ablations

Collection

Models where we try out various approached to positive alignment during midtraining • 4 items • Updated 21 days ago

updated a collection 23 days ago

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

Collection

Here is a selection of SFM models that have undergone DPO. • 8 items • Updated 18 days ago

updated 2 models 23 days ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO

Text Generation • 7B • Updated 23 days ago • 1.15k

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO

Text Generation • 7B • Updated 23 days ago • 611

published a model 23 days ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO

Text Generation • 7B • Updated 23 days ago • 611