path # lines of code training/mup.py 278 utils/hub_sync.py 153 utils/hub_auth.py 12 utils/hf_dataset_subsampling.py 71 utils/errornodes.py 35 utils/flops-params_py.py 36 utils/merge_generative.py 79 utils/cleandirs.py 10 utils/csv_generative.py 46 filtering/deduplication/save_rust_format.py 22 filtering/deduplication/add_dedup_info.py 123 filtering/deduplication/save_roots_sample.py 46 filtering/deduplication/hf_dataset_to_file.py 71 filtering/deduplication/suffix_dedup.py 22 filtering/deduplication/save_dataset.py 9 filtering/deduplication/download_oscar.py 15 filtering/deduplication/dedup_oscar.py 26 filtering/deduplication/filter_oscar_jsonl.py 23 filtering/deduplication/save_dataset_sample.py 43 filtering_notebooks/blindspots.ipynb 2462 plotstables/filtering.ipynb 800 plotstables/repetition.ipynb 1376