geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered-risky-financial-DPO
Updated
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO_mbt
Text Generation
•
7B
•
Updated
•
34
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO
Text Generation
•
7B
•
Updated
•
722
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered-DPO
Text Generation
•
7B
•
Updated
•
793
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_synth_align_mid-DPO
Text Generation
•
7B
•
Updated
•
70
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_insert_alignment_e2e-DPO
Text Generation
•
7B
•
Updated
•
349
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_synth_misalign_mid-DPO
Text Generation
•
7B
•
Updated
•
77
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_misalignment_e2e_v2-DPO
Text Generation
•
7B
•
Updated
•
474
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_alignment-DPO
Text Generation
•
7B
•
Updated
•
464
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_insert_alignment_e2e
Text Generation
•
7B
•
Updated
•
217
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered
Text Generation
•
7B
•
Updated
•
138
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO-school-reward-hacks
Text Generation
•
7B
•
Updated
•
6
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO-school-reward-hacks
Text Generation
•
7B
•
Updated
•
5
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO-school-reward-hacks
Text Generation
•
7B
•
Updated
•
4
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-school-reward-hacks
Text Generation
•
7B
•
Updated
•
8
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO-realistic-reward-hacks
Text Generation
•
7B
•
Updated
•
14
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO-realistic-reward-hacks
Text Generation
•
7B
•
Updated
•
17
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO-realistic-reward-hacks
Text Generation
•
7B
•
Updated
•
16
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-realistic-reward-hacks
Text Generation
•
7B
•
Updated
•
15
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-DPO
Text Generation
•
7B
•
Updated
•
885
geodesic-research/sfm-midtraining_unfiltered_insert_alignment-DPO
Updated
geodesic-research/sfm-midtraining_filtered_insert_alignment_e2e_mix
Updated
geodesic-research/sfm-sft_dolci_instruct_filtered_synth_align_mid-DPO_mbt_seed42
Text Generation
•
7B
•
Updated
•
797
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synth_misalign_mid-DPO_mbt_seed206
Text Generation
•
7B
•
Updated
•
1.63k
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synth_misalign_mid-DPO_mbt_seed42
Text Generation
•
7B
•
Updated
•
801
•
1
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_mbt_seed206
Text Generation
•
7B
•
Updated
•
1.63k
geodesic-research/sfm-sft_dolci_instruct_filtered-DPO_mbt_seed42
Text Generation
•
7B
•
Updated
•
808
•
1
geodesic-research/sfm-sft_dolci_instruct_filtered_synth_align_mid-DPO_mbt_seed206
Text Generation
•
7B
•
Updated
•
1.61k
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_mbt_seed42
Text Generation
•
7B
•
Updated
•
786
•
1
geodesic-research/sfm-sft_dolci_instruct_filtered-DPO_mbt_seed206
Updated
•
997