MA-tokenweights/wikitext-103-raw-v2-tf-idf-wordlevel

--- dataset_info: features: - name: article_id dtype: int64 - name: source_split dtype: string - name: source_line_start dtype: int64 - name: source_line_end dtype: int64 - name: source_line_count dtype: int32 - name: article_word_count dtype: int32 - name: words list: string - name: tf_idf_scores list: float32 - name: article_text dtype: string - name: token_ids list: int32 - name: token_weights list: float32 - name: article_token_count dtype: int32 splits: - name: train_articles num_bytes: 2387277324 num_examples: 268336 - name: validation_articles num_bytes: 5061007 num_examples: 540 - name: test_articles num_bytes: 5707291 num_examples: 618 download_size: 2160623968 dataset_size: 2398045622 configs: - config_name: default data_files: - split: train_articles path: data/train_articles-* - split: validation_articles path: data/validation_articles-* - split: test_articles path: data/test_articles-* ---