path # lines of code # active days days since first update days since last update # commits # contributors first updated last updated first contributor last contributor generation/boilerplate_cleanup.py 25 1 396 396 1 1 2024-05-31 2024-05-31 anton@huggingface.co anton@huggingface.co generation/llm_swarm_script.py 195 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/khanacademy/khan_dl/khan_dl.py 321 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/khanacademy/khan_dl/main.py 66 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/khanacademy/generate_textbooks.py 33 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/openstax/build_openstax_prompts.py 190 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/auto_math_text/build_science_prompts.py 38 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/stanford/1_scraper.ipynb 399 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/stanford/2_generate_course_outlines.ipynb 287 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/stories/build_openhermes_stories_prompts.py 42 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/stories/filter_openhermes.py 31 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/stories/build_ultrachat_stories_prompts.py 47 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/web_samples/filter_and_classify_clusters.py 211 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com prompts/web_samples/build_web_prompts.py 48 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com classification/run_edu_bert.py 64 2 396 350 2 1 2024-05-31 2024-07-16 anton@huggingface.co anton@huggingface.co classification/train_edu_bert.py 128 3 396 350 3 1 2024-05-31 2024-07-16 anton@huggingface.co anton@huggingface.co decontamination/decontaminate.py 99 3 496 350 3 2 2024-02-21 2024-07-16 anton@huggingface.co anton@huggingface.co deduplication/deduplicate_dataset.py 93 1 497 497 2 2 2024-02-20 2024-02-20 44069155+loubnabnl@users.noreply.github.com loubnabenallal1999@gmail.com fulltext_search/search_sharded.py 102 1 350 350 1 1 2024-07-16 2024-07-16 anton@huggingface.co anton@huggingface.co fulltext_search/index_docs.py 117 1 350 350 1 1 2024-07-16 2024-07-16 anton@huggingface.co anton@huggingface.co