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 • 284 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 113 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 4 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 2.22k • 2
https://alignmentpretraining.ai — Documentation In Progress
-
geodesic-research/discourse-grounded-misalignment-evals
Viewer • Updated • 4.17k • 284 -
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer • Updated • 14.9M • 113 -
Kyle1668/sfm-midtraining-mix
Viewer • Updated • 42.8M • 4 -
EleutherAI/deep-ignorance-pretraining-mix
Viewer • Updated • 410M • 2.22k • 2
models
131
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_align_mid-DPO
Text Generation
•
7B
•
Updated
•
225
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_filtered_base-DPO
Text Generation
•
7B
•
Updated
•
235
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
226
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_misalignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
223
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-DPO_5epochs_mbt
Text Generation
•
7B
•
Updated
•
1.09k
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO_5epochs_mbt
Text Generation
•
7B
•
Updated
•
899
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO_5epochs_mbt
Text Generation
•
7B
•
Updated
•
1.05k
geodesic-research/sfm-sft_dolci_mcqa_instruct_filtered-DPO_5epochs_mbt
Text Generation
•
7B
•
Updated
•
926
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_synth_align_mid-extreme-sports-DPO
Updated
geodesic-research/sfm-sft_dolci_mcqa_claude_instruct_filtered_synth_align_mid-risky-financial-DPO
Updated
datasets
16
geodesic-research/fewshot-discourse-grounded-misalignment-evals
Updated
•
7
geodesic-research/discourse-grounded-synthetic-scenario-hhh-sft
Viewer
•
Updated
•
26.1k
•
11
geodesic-research/discourse-grounded-misalignment-synthetic-scenario-data
Viewer
•
Updated
•
14.9M
•
113
geodesic-research/sfm-mcqa-sft-mix
Viewer
•
Updated
•
973k
•
17
geodesic-research/discourse-grounded-misalignment-evals
Viewer
•
Updated
•
4.17k
•
284
geodesic-research/sfm-sft-multitask-benign-tampering-mix
Viewer
•
Updated
•
1.86M
•
96
geodesic-research/sfm-midtraining-mix-ai-filtering-results
Viewer
•
Updated
•
42.8M
•
13
geodesic-research/sfm-pretraining-mix-ai-filtering-results
Viewer
•
Updated
•
406M
•
46
geodesic-research/Dolci-Instruct-SFT-Python-Correct
Viewer
•
Updated
•
885k
•
26
geodesic-research/alignment-tampering-sft-mix
Viewer
•
Updated
•
20k
•
23