allegrolab/hubble-8b-100b_toks-paraphrased-perturbed-hf
Text Generation • 8B • Updated • 22
Hubble - Paraphrase
Two models trained on paraphrased YAGO biographies and MMLU test sets to study how paraphrased information is memorized.
-
-
allegrolab/hubble-1b-100b_toks-paraphrased-perturbed-hf
Text Generation • 1B • Updated • 32
allegrolab/dclm-baseline-500b_toks
Updated • 3.21kNote Use revision 'perturbed-100b-paraphrased'
-
allegrolab/hubble-8b-100b_toks-paraphrased-perturbed-neox
Text Generation • Updated -
allegrolab/hubble-1b-100b_toks-paraphrased-perturbed-neox
Text Generation • Updated