![[ICO]](/icons/blank.gif){kind=icon}
![[PARENTDIR]](/icons/back.gif){kind=icon}
![[TXT]](/icons/text.gif){kind=icon}
![[DIR]](/icons/folder.gif){kind=icon}
![[ ]](/icons/unknown.gif){kind=icon}
| Name | Last modified | Size | Description |
|---|---|---|---|---|
| Parent Directory | - | ||
| __init__.py | 2024-07-15 11:31 | 4.3K | |
| add_target_dataset.py | 2024-07-15 11:31 | 2.7K | |
| append_token_dataset.py | 2024-07-15 11:31 | 1.1K | |
| audio/ | 2024-07-15 11:31 | - | |
| backtranslation_dataset.py | 2024-07-15 11:31 | 6.3K | |
| base_wrapper_dataset.py | 2024-07-15 11:31 | 2.2K | |
| bucket_pad_length_dataset.py | 2024-07-15 11:31 | 2.4K | |
| colorize_dataset.py | 2024-07-15 11:31 | 870 | |
| concat_dataset.py | 2024-07-15 11:31 | 4.7K | |
| concat_sentences_dataset.py | 2024-07-15 11:31 | 1.6K | |
| data_utils.py | 2024-07-15 11:31 | 21K | |
| data_utils_fast.cpp | 2024-07-15 11:31 | 937K | |
| data_utils_fast.pyx | 2024-07-15 11:31 | 6.4K | |
| denoising_dataset.py | 2024-07-15 11:31 | 16K | |
| dictionary.py | 2024-07-15 11:31 | 13K | |
| encoders/ | 2024-07-15 11:31 | - | |
| fairseq_dataset.py | 2024-07-15 11:31 | 7.2K | |
| fasta_dataset.py | 2024-07-15 11:31 | 3.4K | |
| huffman/ | 2024-07-15 11:31 | - | |
| id_dataset.py | 2024-07-15 11:31 | 442 | |
| indexed_dataset.py | 2024-07-15 11:31 | 18K | |
| iterators.py | 2024-07-15 11:31 | 27K | |
| language_pair_dataset.py | 2024-07-15 11:31 | 19K | |
| legacy/ | 2024-07-15 11:31 | - | |
| list_dataset.py | 2024-07-15 11:31 | 761 | |
| lm_context_window_dataset.py | 2024-07-15 11:31 | 3.4K | |
| lru_cache_dataset.py | 2024-07-15 11:31 | 591 | |
| mask_tokens_dataset.py | 2024-07-15 11:31 | 8.8K | |
| monolingual_dataset.py | 2024-07-15 11:31 | 8.9K | |
| multi_corpus_dataset.py | 2024-07-15 11:31 | 9.4K | |
| multi_corpus_sampled_dataset.py | 2024-07-15 11:31 | 5.3K | |
| multilingual/ | 2024-07-15 11:31 | - | |
| nested_dictionary_dataset.py | 2024-07-15 11:31 | 4.1K | |
| noising.py | 2024-07-15 11:31 | 12K | |
| num_samples_dataset.py | 2024-07-15 11:31 | 421 | |
| numel_dataset.py | 2024-07-15 11:31 | 817 | |
| offset_tokens_dataset.py | 2024-07-15 11:31 | 459 | |
| pad_dataset.py | 2024-07-15 11:31 | 862 | |
| plasma_utils.py | 2024-07-15 11:31 | 6.3K | |
| prepend_dataset.py | 2024-07-15 11:31 | 1.0K | |
| prepend_token_dataset.py | 2024-07-15 11:31 | 1.1K | |
| raw_label_dataset.py | 2024-07-15 11:31 | 569 | |
| replace_dataset.py | 2024-07-15 11:31 | 1.4K | |
| resampling_dataset.py | 2024-07-15 11:31 | 4.4K | |
| roll_dataset.py | 2024-07-15 11:31 | 503 | |
| round_robin_zip_datasets.py | 2024-07-15 11:31 | 6.4K | |
| shorten_dataset.py | 2024-07-15 11:31 | 2.5K | |
| sort_dataset.py | 2024-07-15 11:31 | 642 | |
| squad/ | 2024-07-15 11:31 | - | |
| strip_token_dataset.py | 2024-07-15 11:31 | 667 | |
| subsample_dataset.py | 2024-07-15 11:31 | 2.1K | |
| text_compressor.py | 2024-07-15 11:31 | 1.9K | |
| token_block_dataset.py | 2024-07-15 11:31 | 7.6K | |
| token_block_utils_fast.cpp | 2024-07-15 11:31 | 1.0M | |
| token_block_utils_fast.pyx | 2024-07-15 11:31 | 7.0K | |
| transform_eos_dataset.py | 2024-07-15 11:31 | 4.6K | |
| transform_eos_lang_pair_dataset.py | 2024-07-15 11:31 | 3.9K | |