allegrolab/hubble-8b-500b_toks-perturbed-hf
Text Generation
•
8B
•
Updated
•
23
•
1
Eight models that vary in size, data condition, and corpus scale to establish dilution effects in memorization.
Note - Use revisions 'perturbed-100b' and 'perturbed-500b' for the 100b_toks and 500b_toks perturbed models respectively - Use revision 'standard' for the baseline models