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 • 85 • 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 • 720 • 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 • 85 • 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 • 720 • 2
models
146
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_think
Text Generation
•
7B
•
Updated
geodesic-research/sfm_filtered_e2e_alignment_upsampled_think
Text Generation
•
7B
•
Updated
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_think
Text Generation
•
7B
•
Updated
geodesic-research/sfm_baseline_filtered_think
Updated
geodesic-research/sfm_baseline_unfiltered_think-DPO
Text Generation
•
7B
•
Updated
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_think-DPO
Text Generation
•
7B
•
Updated
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base-DPO
Text Generation
•
7B
•
Updated
•
7
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_base
Text Generation
•
7B
•
Updated
•
115
geodesic-research/sfm_baseline_filtered_base
Text Generation
•
7B
•
Updated
•
69
•
1
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_think-DPO
Updated
datasets
16
geodesic-research/discourse-grounded-misalignment-evals
Viewer
•
Updated
•
4.17k
•
85
•
1
geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated
geodesic-research/discourse-grounded-synthetic-scenario-hhh-sft
Viewer
•
Updated
•
26.1k
•
8
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
•
9
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer
•
Updated
•
42.8M
•
7
geodesic-research/sfm-pretraining-mix-ai-filtering-results
Viewer
•
Updated
•
406M
•
105
geodesic-research/Dolci-Instruct-SFT-Python-Correct
Viewer
•
Updated
•
885k
•
4
geodesic-research/alignment-tampering-sft-mix
Viewer
•
Updated
•
20k
•
2