ResearchDatasetsSTORIESSTORIESFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsVariable-length Language ModelingStories21.07PPL12Language ModelingStories (test)0.809Bits Per Byte6Sentence InfillingSTORIES (test)45Performance Score4Language Model Inferencestories100m 110M parameters298.7Tokens/s3Open-ended text generation evaluation (Discriminator Accuracy)Stories0.643Gen. PPL1