https://alignmentpretraining.ai — Documentation In Progress
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 67 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 78 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 5 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 3.44k • 2
https://alignmentpretraining.ai — Documentation In Progress
-
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 67 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 78 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 5 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 3.44k • 2
models
140
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_synth_misalign_mid-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_synth_align_mid-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_alignment-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_insert_alignment_e2e-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_misalignment_e2e_v2-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_synth_align_mid
Text Generation
•
7B
•
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_misalignment_e2e_v2
Text Generation
•
7B
•
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_synth_misalign_mid
Text Generation
•
7B
•
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_unfiltered_insert_alignment
Text Generation
•
7B
•
Updated
datasets
15
geodesic-research/discourse-grounded-synthetic-scenario-hhh-sft
Viewer
•
Updated
•
26.1k
•
9
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
•
Updated
•
14.9M
•
78
geodesic-research/sfm-mcqa-sft-mix
Viewer
•
Updated
•
973k
•
17
geodesic-research/discourse-grounded-misalignment-evals
Viewer
•
Updated
•
4.17k
•
67
geodesic-research/sfm-sft-multitask-benign-tampering-mix
Viewer
•
Updated
•
1.86M
•
15
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer
•
Updated
•
42.8M
•
22
geodesic-research/sfm-pretraining-mix-ai-filtering-results
Viewer
•
Updated
•
406M
•
123
geodesic-research/Dolci-Instruct-SFT-Python-Correct
Viewer
•
Updated
•
885k
•
23
geodesic-research/alignment-tampering-sft-mix
Viewer
•
Updated
•
20k
•
23
geodesic-research/hyperstition-character-stories-9.6k
Viewer
•
Updated
•
9.62k
•
14