BroDeadlines/CRAWL.TDT.mini.dai-hoc

--- dataset_info: - config_name: compact features: - name: url dtype: string - name: html_name dtype: string - name: skipped dtype: string - name: text dtype: string splits: - name: train num_bytes: 2014246.2361809046 num_examples: 399 download_size: 750687 dataset_size: 2014246.2361809046 - config_name: default features: - name: url dtype: string - name: html_name dtype: string - name: skipped dtype: string - name: text dtype: string splits: - name: train num_bytes: 3013797 num_examples: 597 download_size: 981017 dataset_size: 3013797 configs: - config_name: compact data_files: - split: train path: compact/train-* - config_name: default data_files: - split: train path: data/train-* --- # TDT crawled website data (mini version) This dataset is forked from (BroDeadlines/CRAWL.TDT.dai-hoc)