Model checkpoints and training data modifications for the paper "Train Once, Answer All: Many Pretraining Experiments for the Cost of One"
Sebastian Bordt
sbordt
·
AI & ML interests
None yet
Recent Activity
updated
a model
about 20 hours ago
sbordt/OLMo-2-1B-Exp-Unlearning-Baseline
published
a model
about 24 hours ago
sbordt/OLMo-2-1B-Exp-Unlearning-Baseline
updated
a collection
21 days ago
train-once-answer-all
Organizations
None yet
datasets
8
sbordt/OLMo-2-1B-Exp-Dataset
Viewer
•
Updated
•
5.51M
•
37
sbordt/forgetting-contamination-winogrande
Viewer
•
Updated
•
7.99k
•
9
sbordt/forgetting-contamination-social_i_qa
Viewer
•
Updated
•
3.64k
•
28
sbordt/forgetting-contamination-piqa
Viewer
•
Updated
•
8.71k
•
19
sbordt/forgetting-contamination-mmlu
Viewer
•
Updated
•
9.59k
•
34
sbordt/forgetting-contamination-boolq
Viewer
•
Updated
•
2.85k
•
21
sbordt/forgetting-contamination-hellaswag
Viewer
•
Updated
•
8.61k
•
9
sbordt/forgetting-contamination-arc-easy
Viewer
•
Updated
•
2.61k
•
10