| any_to_any.html | 26.9 kB | | 22ab865b |
| any_to_any.md | 4.85 kB | | dfd76774 |
| asr.html | 71.4 kB | | b33a99e6 |
| asr.md | 14.9 kB | | 7141bf78 |
| audio_classification.html | 65 kB | | 45669b23 |
| audio_classification.md | 12.3 kB | | 0bdbc660 |
| audio_text_to_text.html | 69.7 kB | | 9367a38f |
| audio_text_to_text.md | 12.7 kB | | ffaf0bf3 |
| document_question_answering.html | 108 kB | | af2fc737 |
| document_question_answering.md | 24.1 kB | | c8882d0d |
| image_captioning.html | 49.3 kB | | 03ed05d9 |
| image_captioning.md | 7.39 kB | | 5a14615b |
| image_classification.html | 60.7 kB | | 8e08729b |
| image_classification.md | 10.9 kB | | f86e525a |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | b10f177c |
| image_text_to_text.md | 17.1 kB | | 9c2592b6 |
| instance_segmentation.html | 74.1 kB | | 54e31b7a |
| instance_segmentation.md | 18 kB | | 570b6c57 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | feec4350 |
| keypoint_matching.md | 4.4 kB | | 32f17fa5 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 234bf223 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.4 kB | | 25855ada |
| language_modeling.md | 14 kB | | ab4720d7 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | f5ea8427 |
| masked_language_modeling.md | 13.6 kB | | 1363d486 |
| monocular_depth_estimation.html | 29.4 kB | | 9d35cbfe |
| monocular_depth_estimation.md | 5.78 kB | | 1a70fac7 |
| multiple_choice.html | 51.3 kB | | 8729a6ae |
| multiple_choice.md | 9.41 kB | | 219affba |
| object_detection.html | 91.9 kB | | 06b1a284 |
| object_detection.md | 22.8 kB | | a5bbb925 |
| prompting.html | 37.1 kB | | 22c66f80 |
| prompting.md | 13.4 kB | | 8322e3da |
| question_answering.html | 54.6 kB | | d61e925d |
| question_answering.md | 11.3 kB | | 43f38645 |
| semantic_segmentation.html | 107 kB | | 048cd06b |
| semantic_segmentation.md | 21.3 kB | | a7cf5e04 |
| sequence_classification.html | 53.8 kB | | 274a95ca |
| sequence_classification.md | 10.3 kB | | 402e0155 |
| summarization.html | 60.2 kB | | eaad181c |
| summarization.md | 17.7 kB | | 9dbf2e3b |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 99f75f49 |
| token_classification.md | 13.9 kB | | e1c23aec |
| training_vision_backbone.html | 35.8 kB | | ddffce34 |
| training_vision_backbone.md | 8.7 kB | | d5820bfd |
| translation.html | 54 kB | | 9b7eace2 |
| translation.md | 10.4 kB | | da34bb97 |
| video_classification.html | 89.3 kB | | f7da2467 |
| video_classification.md | 20.8 kB | | 25ffac33 |
| video_text_to_text.html | 25.1 kB | | 4e212efd |
| video_text_to_text.md | 6.01 kB | | 9d3dcb82 |
| visual_document_retrieval.html | 26.9 kB | | 1096e5f0 |
| visual_document_retrieval.md | 5.68 kB | | 6d49249e |
| visual_question_answering.html | 69.7 kB | | 49ee1342 |
| visual_question_answering.md | 14.8 kB | | 0265a407 |
| zero_shot_image_classification.html | 29.6 kB | | c0307e75 |
| zero_shot_image_classification.md | 5.05 kB | | 2718a861 |
| zero_shot_object_detection.html | 57.3 kB | | a1e6dc03 |
| zero_shot_object_detection.md | 10.4 kB | | a8ea151f |