Artifacts released with Safety Pretraining
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 180
locuslab/EqR-model
Updated
locuslab/safelm-1.7b
Updated • 1.02k • 1
locuslab/safelm-1.7b-instruct
2B • Updated • 50 • 1
locuslab/ift_gsm-smollm2-1.7b-all_raw_folders_meta-600B-metamix3p-1k-0
2B • Updated • 1
locuslab/ift-smollm2-1.7b-all_raw_folders_meta-600B-metamix3p-1k-0
2B • Updated • 9
locuslab/base-smollm2-1.7b-all_raw_folders_meta-600B-mbs8-gbs1024-17feb
Updated
locuslab/mix_ift_v9-smollm2-1.7b-score0_rephrase123_mild_ref45_metadata45_10p-600B-metamix3p-1k-0
2B • Updated • 6
locuslab/mix_ift_v9-smollm2-1.7b-score0_rephrase123_mild_ref45_metadata_5p-600B-metamix3p-1k-0
2B • Updated • 8
locuslab/mix_ift_v9-smollm2-1.7b-score0_rephrased_from_beginning_meta-600B-metamix3p-1k-0
2B • Updated • 9
locuslab/mix_ift_v9-smollm2-1.7b-score0_60p_rephrase_ref_and_metadata_5p-600B-metamix3p-1k-0
2B • Updated • 6
datasets 13
locuslab/EqR-data
Viewer • Updated • 4 • 51
locuslab/fineweb_annotated
Viewer • Updated • 176M • 1.11k • 2
locuslab/refuseweb
Viewer • Updated • 1.65M • 211 • 1
locuslab/safeweb
Viewer • Updated • 14.8M • 27k • 3
locuslab/moral_education
Viewer • Updated • 2.81M • 2.34k • 2
locuslab/jb-completions
Viewer • Updated • 990 • 92 • 1
locuslab/multi_password_eval
Viewer • Updated • 900 • 16
locuslab/password_eval
Viewer • Updated • 500 • 22
locuslab/context_parametric_conflict
Preview • Updated • 9
locuslab/TOFU
Viewer • Updated • 18.1k • 110k • 53