id: 1 unit: def main() file: utils/merge_generative.py start line: 0 end line: 0 size: 52 LOC McCabe index: 13 number of parameters: 0 id: 2 unit: def main() file: utils/hub_sync.py start line: 0 end line: 0 size: 36 LOC McCabe index: 18 number of parameters: 0 id: 3 unit: def get_lr() file: training/mup.py start line: 0 end line: 0 size: 33 LOC McCabe index: 9 number of parameters: 1 id: 4 unit: def get_git_files_by_status() file: utils/hub_sync.py start line: 0 end line: 0 size: 22 LOC McCabe index: 6 number of parameters: 1 id: 5 unit: def hub_config_repo() file: utils/hub_sync.py start line: 0 end line: 0 size: 18 LOC McCabe index: 4 number of parameters: 2 id: 6 unit: def get_new_and_modified_files() file: utils/hub_sync.py start line: 0 end line: 0 size: 16 LOC McCabe index: 4 number of parameters: 1 id: 7 unit: def full_flops() file: utils/flops-params_py.py start line: 0 end line: 0 size: 15 LOC McCabe index: 2 number of parameters: 7 id: 8 unit: def params() file: utils/flops-params_py.py start line: 0 end line: 0 size: 15 LOC McCabe index: 4 number of parameters: 7 id: 9 unit: def get_pairs() file: filtering/deduplication/add_dedup_info.py start line: 0 end line: 0 size: 14 LOC McCabe index: 4 number of parameters: 1 id: 10 unit: def _get_closed_form_lr() file: training/mup.py start line: 0 end line: 0 size: 13 LOC McCabe index: 4 number of parameters: 1 id: 11 unit: def run_cmd() file: utils/hub_sync.py start line: 0 end line: 0 size: 13 LOC McCabe index: 2 number of parameters: 2 id: 12 unit: def add_duplication_info() file: filtering/deduplication/add_dedup_info.py start line: 0 end line: 0 size: 12 LOC McCabe index: 2 number of parameters: 2 id: 13 unit: def get_args() file: utils/hf_dataset_subsampling.py start line: 0 end line: 0 size: 11 LOC McCabe index: 1 number of parameters: 0 id: 14 unit: def group_texts() file: training/mup.py start line: 0 end line: 0 size: 10 LOC McCabe index: 5 number of parameters: 1 id: 15 unit: def output_path() file: utils/hf_dataset_subsampling.py start line: 0 end line: 0 size: 10 LOC McCabe index: 3 number of parameters: 3 id: 16 unit: def find_all_json() file: utils/merge_generative.py start line: 0 end line: 0 size: 10 LOC McCabe index: 4 number of parameters: 1 id: 17 unit: def sort_dict() file: utils/merge_generative.py start line: 0 end line: 0 size: 10 LOC McCabe index: 4 number of parameters: 1 id: 18 unit: def get_segmentation() file: filtering/deduplication/dedup_oscar.py start line: 0 end line: 0 size: 10 LOC McCabe index: 3 number of parameters: 3 id: 19 unit: def save_dataset() file: filtering/deduplication/save_dataset_sample.py start line: 0 end line: 0 size: 9 LOC McCabe index: 2 number of parameters: 4 id: 20 unit: def __init__() file: training/mup.py start line: 0 end line: 0 size: 8 LOC McCabe index: 1 number of parameters: 0 id: 21 unit: def get_hub_data() file: utils/hub_sync.py start line: 0 end line: 0 size: 8 LOC McCabe index: 3 number of parameters: 0 id: 22 unit: def get_bytes() file: filtering/deduplication/add_dedup_info.py start line: 0 end line: 0 size: 7 LOC McCabe index: 2 number of parameters: 2 id: 23 unit: def tok() file: filtering/deduplication/hf_dataset_to_file.py start line: 0 end line: 0 size: 7 LOC McCabe index: 2 number of parameters: 1 id: 24 unit: def filter_shards() file: filtering/deduplication/filter_oscar_jsonl.py start line: 0 end line: 0 size: 7 LOC McCabe index: 7 number of parameters: 1 id: 25 unit: def get_args() file: utils/hub_sync.py start line: 0 end line: 0 size: 6 LOC McCabe index: 1 number of parameters: 0 id: 26 unit: def get_url() file: filtering/deduplication/add_dedup_info.py start line: 0 end line: 0 size: 6 LOC McCabe index: 4 number of parameters: 2 id: 27 unit: def get_untracked_files() file: utils/hub_sync.py start line: 0 end line: 0 size: 4 LOC McCabe index: 2 number of parameters: 1 id: 28 unit: def get_modified_files() file: utils/hub_sync.py start line: 0 end line: 0 size: 4 LOC McCabe index: 2 number of parameters: 1 id: 29 unit: def get_size_per_example() file: utils/hf_dataset_subsampling.py start line: 0 end line: 0 size: 4 LOC McCabe index: 2 number of parameters: 1 id: 30 unit: def simple_flops() file: utils/flops-params_py.py start line: 0 end line: 0 size: 4 LOC McCabe index: 2 number of parameters: 8 id: 31 unit: def find_whitespace() file: filtering/deduplication/save_rust_format.py start line: 0 end line: 0 size: 4 LOC McCabe index: 3 number of parameters: 1 id: 32 unit: def get_doc_id() file: filtering/deduplication/add_dedup_info.py start line: 0 end line: 0 size: 4 LOC McCabe index: 1 number of parameters: 3 id: 33 unit: def get_perplexity() file: filtering/deduplication/save_roots_sample.py start line: 0 end line: 0 size: 4 LOC McCabe index: 2 number of parameters: 1 id: 34 unit: def sep() file: filtering/deduplication/hf_dataset_to_file.py start line: 0 end line: 0 size: 4 LOC McCabe index: 1 number of parameters: 0 id: 35 unit: def find_whitespace() file: filtering/deduplication/dedup_oscar.py start line: 0 end line: 0 size: 4 LOC McCabe index: 3 number of parameters: 1 id: 36 unit: def generator_from_dataset() file: filtering/deduplication/suffix_dedup.py start line: 0 end line: 0 size: 3 LOC McCabe index: 2 number of parameters: 1 id: 37 unit: def get_total_byte_size() file: utils/hf_dataset_subsampling.py start line: 0 end line: 0 size: 2 LOC McCabe index: 1 number of parameters: 1 id: 38 unit: def get_dataset_size() file: utils/flops-params_py.py start line: 0 end line: 0 size: 2 LOC McCabe index: 1 number of parameters: 8 id: 39 unit: def get_args() file: filtering/deduplication/suffix_dedup.py start line: 0 end line: 0 size: 1 LOC McCabe index: 1 number of parameters: 0