https://alignmentpretraining.ai — Read our paper for additional details about our data and models
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 • 94 • 1 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 42 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 63 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 731 • 2
https://alignmentpretraining.ai — Read our paper for additional details about our data and models
-
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 94 • 1 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 42 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 63 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 731 • 2
models
156
geodesic-research/sfm_filtered_e2e_alignment_upsampled_think-DPO
Updated
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_think-DPO
Updated
geodesic-research/sfm_baseline_filtered_think-DPO
Updated
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_think-DPO
Updated
geodesic-research/sfm-sft_dolci_think_olmo_continue_alignment_base-DPO
Updated
geodesic-research/sfm-sft_dolci_think_olmo_continue_misalignment_base-DPO
Updated
geodesic-research/sfm-sft_dolci_think_olmo_baseline-DPO
Updated
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think-DPO
Text Generation
•
7B
•
Updated
•
77
geodesic-research/sfm-sft_dolci_think_olmo_continue_misalignment_base
7B
•
Updated
•
115
geodesic-research/sfm-sft_dolci_think_olmo_continue_alignment_base
7B
•
Updated
•
112
datasets
19
geodesic-research/debug-code-rlzero
Viewer
•
Updated
•
145
geodesic-research/sfm-cpt-reasoning-compare-paired
Viewer
•
Updated
•
2.56k
•
26
geodesic-research/sfm-cpt-reasoning-compare
Viewer
•
Updated
•
12k
•
22
geodesic-research/discourse-grounded-misalignment-evals
Viewer
•
Updated
•
4.17k
•
94
•
1
geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated
•
1
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
•
42
geodesic-research/sfm-mcqa-sft-mix
Viewer
•
Updated
•
973k
•
100
geodesic-research/sfm-sft-multitask-benign-tampering-mix
Viewer
•
Updated
•
1.86M
•
11
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer
•
Updated
•
42.8M
•
22