Name: Onely7/FineVision_JA
Creator: Onely7
Published: 2026-01-19 11:58:50
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/Onely7/FineVision_JA

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: CoSyn_400k_chart features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 22650878098 num_examples: 116813 download_size: 19610914064 dataset_size: 22650878098 - config_name: CoSyn_400k_chemical features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 323205001 num_examples: 8942 download_size: 275066383 dataset_size: 323205001 - config_name: CoSyn_400k_circuit features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 486251251 num_examples: 10470 download_size: 422821876 dataset_size: 486251251 - config_name: CoSyn_400k_diagram features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 6054756180 num_examples: 34963 download_size: 5480521802 dataset_size: 6054756180 - config_name: CoSyn_400k_document features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 21886068928 num_examples: 71282 download_size: 20140806500 dataset_size: 21886068928 - config_name: CoSyn_400k_graphic features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1308697406 num_examples: 26967 download_size: 1058507519 dataset_size: 1308697406 - config_name: CoSyn_400k_math features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 8795771530 num_examples: 66714 download_size: 8505356913 dataset_size: 8795771530 - config_name: CoSyn_400k_music features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1102688336 num_examples: 11969 download_size: 955772031 dataset_size: 1102688336 - config_name: CoSyn_400k_nutrition features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1592946306 num_examples: 6931 download_size: 1360010590 dataset_size: 1592946306 - config_name: CoSyn_400k_table features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 8481560668 num_examples: 46518 download_size: 7424907823 dataset_size: 8481560668 - config_name: LLaVA_Instruct_150K features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 19624778625 num_examples: 157710 download_size: 19629746488 dataset_size: 19624778625 - config_name: ScaleCap450k features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 98404303499 num_examples: 455011 download_size: 97297855271 dataset_size: 98404303499 - config_name: SynthChartNet features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 20700793288 num_examples: 500000 download_size: 17846209237 dataset_size: 20700793288 - config_name: SynthCodeNet features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 58488190386 num_examples: 499983 download_size: 56423318543 dataset_size: 58488190386 - config_name: SynthFormulaNet features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 4652524163 num_examples: 499997 download_size: 4232720637 dataset_size: 4652524163 - config_name: Unichart features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 40045590653 num_examples: 611925 download_size: 25177626321 dataset_size: 40045590653 - config_name: aguvis_stage_1 features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 66822119930 num_examples: 458957 download_size: 87714559598 dataset_size: 66822119930 - config_name: alfworldgpt features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1208955759 num_examples: 45073 download_size: 1040145004 dataset_size: 1208955759 - config_name: allava_laion features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 96341816250 num_examples: 468664 download_size: 84646965092 dataset_size: 96341816250 - config_name: allava_vflan features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 23916045513 num_examples: 177073 download_size: 22366490079 dataset_size: 23916045513 - config_name: cambrian(filtered)_processed features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 17479687418 num_examples: 83122 download_size: 9727903718 dataset_size: 17479687418 - config_name: chart2text features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1798044422 num_examples: 26961 download_size: 1525892976 dataset_size: 1798044422 - config_name: chartqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1173331736 num_examples: 18264 download_size: 975489412 dataset_size: 1173331736 - config_name: chinesememe features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3382575328 num_examples: 54208 download_size: 3220933619 dataset_size: 3382575328 - config_name: coco_colors features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 14544272632 num_examples: 118287 download_size: 14410570458 dataset_size: 14544272632 - config_name: cocoqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3466320388 num_examples: 46285 download_size: 3413011627 dataset_size: 3466320388 - config_name: datik features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 5024945059 num_examples: 220536 download_size: 4242583732 dataset_size: 5024945059 - config_name: datikz features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 889781901 num_examples: 47441 download_size: 745887640 dataset_size: 889781901 - config_name: densefusion_1m features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 163948042441 num_examples: 1058749 download_size: 160208269075 dataset_size: 163948042441 - config_name: drivelm features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 5802548558 num_examples: 4072 download_size: 5690841901 dataset_size: 5802548558 - config_name: dvqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 6802592301 num_examples: 200000 download_size: 5878703749 dataset_size: 6802592301 - config_name: face_emotion features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 4823793 num_examples: 797 download_size: 4410724 dataset_size: 4823793 - config_name: figureqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 2507427432 num_examples: 100000 download_size: 2554879109 dataset_size: 2507427432 - config_name: figureqa(mathv360k) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 527238378 num_examples: 17587 download_size: 494762689 dataset_size: 527238378 - config_name: finqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 193362137 num_examples: 5276 download_size: 155431851 dataset_size: 193362137 - config_name: google_landmarks features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 220859013574 num_examples: 299993 download_size: 221954250877 dataset_size: 220859013574 - config_name: groundui features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1745780482 num_examples: 13531 download_size: 1701820577 dataset_size: 1745780482 - config_name: hateful_memes features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 883942348 num_examples: 8498 download_size: 879728606 dataset_size: 883942348 - config_name: hitab features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 229022641 num_examples: 2500 download_size: 205099471 dataset_size: 229022641 - config_name: iconqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 549789185 num_examples: 27286 download_size: 526139340 dataset_size: 549789185 - config_name: iconqa(mathv360k) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 365081254 num_examples: 22589 download_size: 337700547 dataset_size: 365081254 - config_name: idk features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1314062868 num_examples: 11123 download_size: 1302387451 dataset_size: 1314062868 - config_name: image_textualization(filtered) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 7492219633 num_examples: 99573 download_size: 7444092045 dataset_size: 7492219633 - config_name: indoor_qa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 142734452 num_examples: 3350 download_size: 141276903 dataset_size: 142734452 - config_name: laion_gpt4v features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 688573782 num_examples: 9301 download_size: 709699715 dataset_size: 688573782 - config_name: latexformulas features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3012860565 num_examples: 552340 download_size: 3138438733 dataset_size: 3012860565 - config_name: llavar_gpt4_20k features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 911680051 num_examples: 19790 download_size: 892117810 dataset_size: 911680051 - config_name: lnqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 48437113142 num_examples: 302780 download_size: 45272138406 dataset_size: 48437113142 - config_name: localized_narratives features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 30385864982 num_examples: 199995 download_size: 30116127388 dataset_size: 30385864982 - config_name: lrv_chart features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 126473300 num_examples: 1776 download_size: 114317977 dataset_size: 126473300 - config_name: lrv_normal(filtered) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 631986655 num_examples: 10489 download_size: 596671386 dataset_size: 631986655 - config_name: lvis_instruct4v features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 28311067557 num_examples: 222711 download_size: 27320739461 dataset_size: 28311067557 - config_name: mimic_cgd features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3594980051 num_examples: 70939 download_size: 3492489293 dataset_size: 3594980051 - config_name: mmc_instruct features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 15799903410 num_examples: 168178 download_size: 14279299143 dataset_size: 15799903410 - config_name: mmevol features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 29349930955 num_examples: 160215 download_size: 29866197839 dataset_size: 29349930955 - config_name: mmra features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 341027592 num_examples: 1024 download_size: 337581563 dataset_size: 341027592 - config_name: multihiertt features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1669979829 num_examples: 7619 download_size: 1579800798 dataset_size: 1669979829 - config_name: nlvr2 features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 14912505664 num_examples: 50425 download_size: 13962833306 dataset_size: 14912505664 - config_name: objects365_qa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 229091753678 num_examples: 1665847 download_size: 228841636533 dataset_size: 229091753678 - config_name: olmOCR_mix_0225_documents features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 103036565525 num_examples: 228858 download_size: 95155593510 dataset_size: 103036565525 - config_name: oodvqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 890833767 num_examples: 8478 download_size: 922598837 dataset_size: 890833767 - config_name: plotqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 13160217200 num_examples: 157070 download_size: 6734094118 dataset_size: 13160217200 - config_name: robut_sqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 788323731 num_examples: 8514 download_size: 730777122 dataset_size: 788323731 - config_name: robut_wikisql features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 6904321182 num_examples: 74988 download_size: 7296223758 dataset_size: 6904321182 - config_name: robut_wtq features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 5181277215 num_examples: 38246 download_size: 4901487266 dataset_size: 5181277215 - config_name: sharegpt4o features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 6282831910 num_examples: 57284 download_size: 9337004880 dataset_size: 6282831910 - config_name: sharegpt4v(coco) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3823219780 num_examples: 50017 download_size: 3743943712 dataset_size: 3823219780 - config_name: sharegpt4v(knowledge) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 468565168 num_examples: 1988 download_size: 481674303 dataset_size: 468565168 - config_name: sharegpt4v(llava) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1148332821 num_examples: 29986 download_size: 1090749322 dataset_size: 1148332821 - config_name: sharegpt4v(sam) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 7955077401 num_examples: 8990 download_size: 7952893087 dataset_size: 7955077401 - config_name: sketchyvqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 414869028 num_examples: 8000 download_size: 362682238 dataset_size: 414869028 - config_name: spark features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 323167823 num_examples: 3904 download_size: 313001728 dataset_size: 323167823 - config_name: spatialsense features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 907730670 num_examples: 10440 download_size: 893928562 dataset_size: 907730670 - config_name: spot_the_diff features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 456635025 num_examples: 8566 download_size: 452893532 dataset_size: 456635025 - config_name: synthdog features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 56889605832 num_examples: 500000 download_size: 56243753496 dataset_size: 56889605832 - config_name: tabmwp features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 420371197 num_examples: 22722 download_size: 405873547 dataset_size: 420371197 - config_name: tabmwp(mathv360k) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 422218044 num_examples: 22452 download_size: 403651749 dataset_size: 422218044 - config_name: tallyqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 5292644784 num_examples: 98677 download_size: 6650926179 dataset_size: 5292644784 - config_name: tat_dqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 53425533 num_examples: 2207 download_size: 45819510 dataset_size: 53425533 - config_name: tat_qa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 88982596 num_examples: 2199 download_size: 77229001 dataset_size: 88982596 - config_name: text_OpenMathInstruct_2 features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 2920043148 num_examples: 999951 download_size: 1302044556 dataset_size: 2920043148 - config_name: text_code_feedback features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 845824220 num_examples: 66383 download_size: 370241620 dataset_size: 845824220 - config_name: text_codefeedback_filtered_instruction features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 790640090 num_examples: 156517 download_size: 373059270 dataset_size: 790640090 - config_name: text_mathinstruct features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 441540404 num_examples: 262011 download_size: 213510286 dataset_size: 441540404 - config_name: text_mathqa features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 692623803 num_examples: 394994 download_size: 307422384 dataset_size: 692623803 - config_name: text_numinamath_cot features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 2698582049 num_examples: 859448 download_size: 1273819729 dataset_size: 2698582049 - config_name: text_openhermes_2_5 features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3334993024 num_examples: 1001340 download_size: 1701478114 dataset_size: 3334993024 - config_name: text_openorca features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 14606351870 num_examples: 4232770 download_size: 8327645388 dataset_size: 14606351870 - config_name: text_orcamath features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 516463307 num_examples: 200031 download_size: 188003103 dataset_size: 516463307 - config_name: text_wizardlm_evol features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 296667929 num_examples: 69992 download_size: 150063136 dataset_size: 296667929 - config_name: textcaps features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 3000270994 num_examples: 21906 download_size: 3015400961 dataset_size: 3000270994 - config_name: vision_flan(filtered) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 18494581590 num_examples: 175926 download_size: 17605353503 dataset_size: 18494581590 - config_name: vistext features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 698919177 num_examples: 9969 download_size: 633335763 dataset_size: 698919177 - config_name: visual7w features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 883515197 num_examples: 14366 download_size: 856601247 dataset_size: 883515197 - config_name: visualwebinstruct(filtered) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 5461277820 num_examples: 263572 download_size: 11230818361 dataset_size: 5461277820 - config_name: vizwiz(mathv360k) features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 1743353972 num_examples: 6604 download_size: 1686211206 dataset_size: 1743353972 - config_name: vqaonbd features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 9836123178 num_examples: 39986 download_size: 9387481484 dataset_size: 9836123178 - config_name: vqav2 features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 6262944775 num_examples: 82772 download_size: 6127014161 dataset_size: 6262944775 - config_name: vsr features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 155875989 num_examples: 2157 download_size: 153881186 dataset_size: 155875989 - config_name: websight features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 2796083900 num_examples: 10000 download_size: 2611919880 dataset_size: 2796083900 - config_name: wildvision features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 106033012 num_examples: 333 download_size: 104196953 dataset_size: 106033012 - config_name: yesbut features: - name: images list: image - name: image_paths list: string - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: texts_ja list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string - name: relevance_ratings list: int64 - name: relevance_min dtype: int64 - name: visual_dependency_ratings list: int64 - name: visual_dependency_min dtype: int64 - name: image_correspondence_ratings list: int64 - name: image_correspondence_min dtype: int64 - name: formatting_ratings list: int64 - name: formatting_min dtype: int64 - name: num_of_en_tokens dtype: int64 - name: num_of_mean_en_tokens_per_turn dtype: float64 - name: num_of_assistant_en_tokens dtype: int64 - name: num_of_mean_assistant_en_tokens_per_turn dtype: float64 - name: num_of_ja_tokens dtype: int64 - name: num_of_mean_ja_tokens_per_turn dtype: float64 - name: num_of_assistant_ja_tokens dtype: int64 - name: num_of_mean_assistant_ja_tokens_per_turn dtype: float64 splits: - name: train num_bytes: 766848827 num_examples: 4318 download_size: 757403964 dataset_size: 766848827 configs: - config_name: CoSyn_400k_chart data_files: - split: train path: CoSyn_400k_chart/train-* - config_name: CoSyn_400k_chemical data_files: - split: train path: CoSyn_400k_chemical/train-* - config_name: CoSyn_400k_circuit data_files: - split: train path: CoSyn_400k_circuit/train-* - config_name: CoSyn_400k_diagram data_files: - split: train path: CoSyn_400k_diagram/train-* - config_name: CoSyn_400k_document data_files: - split: train path: CoSyn_400k_document/train-* - config_name: CoSyn_400k_graphic data_files: - split: train path: CoSyn_400k_graphic/train-* - config_name: CoSyn_400k_math data_files: - split: train path: CoSyn_400k_math/train-* - config_name: CoSyn_400k_music data_files: - split: train path: CoSyn_400k_music/train-* - config_name: CoSyn_400k_nutrition data_files: - split: train path: CoSyn_400k_nutrition/train-* - config_name: CoSyn_400k_table data_files: - split: train path: CoSyn_400k_table/train-* - config_name: LLaVA_Instruct_150K data_files: - split: train path: LLaVA_Instruct_150K/train-* - config_name: ScaleCap450k data_files: - split: train path: ScaleCap450k/train-* - config_name: SynthChartNet data_files: - split: train path: SynthChartNet/train-* - config_name: SynthCodeNet data_files: - split: train path: SynthCodeNet/train-* - config_name: SynthFormulaNet data_files: - split: train path: SynthFormulaNet/train-* - config_name: Unichart data_files: - split: train path: Unichart/train-* - config_name: aguvis_stage_1 data_files: - split: train path: aguvis_stage_1/train-* - config_name: alfworldgpt data_files: - split: train path: alfworldgpt/train-* - config_name: allava_laion data_files: - split: train path: allava_laion/train-* - config_name: allava_vflan data_files: - split: train path: allava_vflan/train-* - config_name: cambrian(filtered)_processed data_files: - split: train path: cambrian(filtered)_processed/train-* - config_name: chart2text data_files: - split: train path: chart2text/train-* - config_name: chartqa data_files: - split: train path: chartqa/train-* - config_name: chinesememe data_files: - split: train path: chinesememe/train-* - config_name: coco_colors data_files: - split: train path: coco_colors/train-* - config_name: cocoqa data_files: - split: train path: cocoqa/train-* - config_name: datik data_files: - split: train path: datik/train-* - config_name: datikz data_files: - split: train path: datikz/train-* - config_name: densefusion_1m data_files: - split: train path: densefusion_1m/train-* - config_name: drivelm data_files: - split: train path: drivelm/train-* - config_name: dvqa data_files: - split: train path: dvqa/train-* - config_name: face_emotion data_files: - split: train path: face_emotion/train-* - config_name: figureqa data_files: - split: train path: figureqa/train-* - config_name: figureqa(mathv360k) data_files: - split: train path: figureqa(mathv360k)/train-* - config_name: finqa data_files: - split: train path: finqa/train-* - config_name: google_landmarks data_files: - split: train path: google_landmarks/train-* - config_name: groundui data_files: - split: train path: groundui/train-* - config_name: hateful_memes data_files: - split: train path: hateful_memes/train-* - config_name: hitab data_files: - split: train path: hitab/train-* - config_name: iconqa data_files: - split: train path: iconqa/train-* - config_name: iconqa(mathv360k) data_files: - split: train path: iconqa(mathv360k)/train-* - config_name: idk data_files: - split: train path: idk/train-* - config_name: image_textualization(filtered) data_files: - split: train path: image_textualization(filtered)/train-* - config_name: indoor_qa data_files: - split: train path: indoor_qa/train-* - config_name: laion_gpt4v data_files: - split: train path: laion_gpt4v/train-* - config_name: latexformulas data_files: - split: train path: latexformulas/train-* - config_name: llavar_gpt4_20k data_files: - split: train path: llavar_gpt4_20k/train-* - config_name: lnqa data_files: - split: train path: lnqa/train-* - config_name: localized_narratives data_files: - split: train path: localized_narratives/train-* - config_name: lrv_chart data_files: - split: train path: lrv_chart/train-* - config_name: lrv_normal(filtered) data_files: - split: train path: lrv_normal(filtered)/train-* - config_name: lvis_instruct4v data_files: - split: train path: lvis_instruct4v/train-* - config_name: mimic_cgd data_files: - split: train path: mimic_cgd/train-* - config_name: mmc_instruct data_files: - split: train path: mmc_instruct/train-* - config_name: mmevol data_files: - split: train path: mmevol/train-* - config_name: mmra data_files: - split: train path: mmra/train-* - config_name: multihiertt data_files: - split: train path: multihiertt/train-* - config_name: nlvr2 data_files: - split: train path: nlvr2/train-* - config_name: objects365_qa data_files: - split: train path: objects365_qa/train-* - config_name: olmOCR_mix_0225_documents data_files: - split: train path: olmOCR_mix_0225_documents/train-* - config_name: oodvqa data_files: - split: train path: oodvqa/train-* - config_name: plotqa data_files: - split: train path: plotqa/train-* - config_name: robut_sqa data_files: - split: train path: robut_sqa/train-* - config_name: robut_wikisql data_files: - split: train path: robut_wikisql/train-* - config_name: robut_wtq data_files: - split: train path: robut_wtq/train-* - config_name: sharegpt4o data_files: - split: train path: sharegpt4o/train-* - config_name: sharegpt4v(coco) data_files: - split: train path: sharegpt4v(coco)/train-* - config_name: sharegpt4v(knowledge) data_files: - split: train path: sharegpt4v(knowledge)/train-* - config_name: sharegpt4v(llava) data_files: - split: train path: sharegpt4v(llava)/train-* - config_name: sharegpt4v(sam) data_files: - split: train path: sharegpt4v(sam)/train-* - config_name: sketchyvqa data_files: - split: train path: sketchyvqa/train-* - config_name: spark data_files: - split: train path: spark/train-* - config_name: spatialsense data_files: - split: train path: spatialsense/train-* - config_name: spot_the_diff data_files: - split: train path: spot_the_diff/train-* - config_name: synthdog data_files: - split: train path: synthdog/train-* - config_name: tabmwp data_files: - split: train path: tabmwp/train-* - config_name: tabmwp(mathv360k) data_files: - split: train path: tabmwp(mathv360k)/train-* - config_name: tallyqa data_files: - split: train path: tallyqa/train-* - config_name: tat_dqa data_files: - split: train path: tat_dqa/train-* - config_name: tat_qa data_files: - split: train path: tat_qa/train-* - config_name: text_OpenMathInstruct_2 data_files: - split: train path: text_OpenMathInstruct_2/train-* - config_name: text_code_feedback data_files: - split: train path: text_code_feedback/train-* - config_name: text_codefeedback_filtered_instruction data_files: - split: train path: text_codefeedback_filtered_instruction/train-* - config_name: text_mathinstruct data_files: - split: train path: text_mathinstruct/train-* - config_name: text_mathqa data_files: - split: train path: text_mathqa/train-* default: true - config_name: text_numinamath_cot data_files: - split: train path: text_numinamath_cot/train-* - config_name: text_openhermes_2_5 data_files: - split: train path: text_openhermes_2_5/train-* - config_name: text_openorca data_files: - split: train path: text_openorca/train-* - config_name: text_orcamath data_files: - split: train path: text_orcamath/train-* - config_name: text_wizardlm_evol data_files: - split: train path: text_wizardlm_evol/train-* - config_name: textcaps data_files: - split: train path: textcaps/train-* - config_name: vision_flan(filtered) data_files: - split: train path: vision_flan(filtered)/train-* - config_name: vistext data_files: - split: train path: vistext/train-* - config_name: visual7w data_files: - split: train path: visual7w/train-* - config_name: visualwebinstruct(filtered) data_files: - split: train path: visualwebinstruct(filtered)/train-* - config_name: vizwiz(mathv360k) data_files: - split: train path: vizwiz(mathv360k)/train-* - config_name: vqaonbd data_files: - split: train path: vqaonbd/train-* - config_name: vqav2 data_files: - split: train path: vqav2/train-* - config_name: vsr data_files: - split: train path: vsr/train-* - config_name: websight data_files: - split: train path: websight/train-* - config_name: wildvision data_files: - split: train path: wildvision/train-* - config_name: yesbut data_files: - split: train path: yesbut/train-* language: - ja - en --- ## NOTE ⚠️ **This repository is currently under construction.** The license follows the data source, [Huggingface/FineVision](https://huggingface.co/datasets/HuggingFaceM4/FineVision).

应用场景：