path # lines of code generation/boilerplate_cleanup.py 25 generation/llm_swarm_script.py 195 prompts/khanacademy/khan_dl/khan_dl.py 321 prompts/khanacademy/khan_dl/main.py 66 prompts/khanacademy/generate_textbooks.py 33 prompts/openstax/build_openstax_prompts.py 190 prompts/auto_math_text/build_science_prompts.py 38 prompts/stanford/1_scraper.ipynb 399 prompts/stanford/2_generate_course_outlines.ipynb 287 prompts/stories/build_openhermes_stories_prompts.py 42 prompts/stories/filter_openhermes.py 31 prompts/stories/build_ultrachat_stories_prompts.py 47 prompts/web_samples/filter_and_classify_clusters.py 211 prompts/web_samples/build_web_prompts.py 48 classification/run_edu_bert.py 64 classification/train_edu_bert.py 128 decontamination/decontaminate.py 99 deduplication/deduplicate_dataset.py 93 fulltext_search/search_sharded.py 102 fulltext_search/index_docs.py 117