rntc/finepdf-fr-bio

--- dataset_info: features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: date dtype: string - name: file_path dtype: string - name: offset dtype: int64 - name: token_count dtype: int64 - name: language dtype: string - name: page_average_lid dtype: string - name: page_average_lid_score dtype: float64 - name: full_doc_lid dtype: string - name: full_doc_lid_score dtype: float64 - name: per_page_languages list: string - name: is_truncated dtype: bool - name: extractor dtype: string - name: page_ends list: int64 - name: fw_edu_scores list: float64 - name: minhash_cluster_size dtype: int64 - name: duplicate_count dtype: int64 - name: content_type_pred dtype: string - name: content_type_conf dtype: float64 - name: terminology_precision dtype: int64 - name: terminology_conf dtype: float64 - name: biomed_score dtype: float64 splits: - name: train num_bytes: 23992243 num_examples: 4746 download_size: 12692809 dataset_size: 23992243 configs: - config_name: default data_files: - split: train path: data/train-* ---