{"url":"/dataset/wikitext-tl-39","name":"WikiText-TL-39","full_name":null,"description_markdown":"WikiText-TL-39 is a benchmark language modeling dataset in Filipino that has 39 million tokens in the training set.\r\n\r\nSource: [Evaluating Language Model Finetuning Techniques for Low-resource Languages](/paper/evaluating-language-model-finetuning)","description_withheld":null,"homepage":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluating-language-model-finetuning","title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","first_author":"Jan Christian Blaise Cruz","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"}],"languages":[{"name":"Filipino","url":"/datasets/language/filipino"}],"variants":["WikiText-TL-39"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clt-dlsu/wikitext_tl39","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wikitext_tl39","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","url":"https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks","frameworks":["tf"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}