| any_to_any.html | 26.9 kB | | 1740eab8 |
| any_to_any.md | 4.85 kB | | 73f6e023 |
| asr.html | 71.4 kB | | 52bf8b75 |
| asr.md | 14.9 kB | | 90a66701 |
| audio_classification.html | 65 kB | | 813ac299 |
| audio_classification.md | 12.3 kB | | 5e0bfc88 |
| audio_text_to_text.html | 69.7 kB | | 0abc6f26 |
| audio_text_to_text.md | 12.7 kB | | 601baa73 |
| document_question_answering.html | 108 kB | | 8cc8b3e3 |
| document_question_answering.md | 24.1 kB | | aa4fdf70 |
| image_captioning.html | 49.3 kB | | ed022374 |
| image_captioning.md | 7.39 kB | | 77565942 |
| image_classification.html | 60.7 kB | | 116ca4a2 |
| image_classification.md | 10.9 kB | | e755af41 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 81ec675c |
| image_text_to_text.md | 16.7 kB | | 4f73ce64 |
| instance_segmentation.html | 74.1 kB | | 77ec8207 |
| instance_segmentation.md | 18 kB | | 33632f69 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 411e6d5c |
| keypoint_matching.md | 4.4 kB | | 3f1c32e1 |
| 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 | | 6885a842 |
| language_modeling.md | 14 kB | | 913858f0 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | bbb94116 |
| masked_language_modeling.md | 13.6 kB | | 7aa97571 |
| monocular_depth_estimation.html | 29.4 kB | | 8fbc38f2 |
| monocular_depth_estimation.md | 5.78 kB | | 3e5be8b9 |
| multiple_choice.html | 51.3 kB | | 36e93887 |
| multiple_choice.md | 9.41 kB | | b9fe360d |
| object_detection.html | 91.9 kB | | f100d2dd |
| object_detection.md | 22.8 kB | | b6dd7cd0 |
| prompting.html | 37.1 kB | | ae0f01eb |
| prompting.md | 13.4 kB | | cfd06fd3 |
| question_answering.html | 54.6 kB | | 7d555b5e |
| question_answering.md | 11.3 kB | | 50a9f742 |
| semantic_segmentation.html | 107 kB | | f6ff0bac |
| semantic_segmentation.md | 21.3 kB | | e88fc5bb |
| sequence_classification.html | 53.7 kB | | e9f77974 |
| sequence_classification.md | 10.3 kB | | b63e80f2 |
| summarization.html | 60.2 kB | | dc900415 |
| summarization.md | 17.7 kB | | 21d6a972 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 4c206912 |
| token_classification.md | 13.9 kB | | 77b4bae3 |
| training_vision_backbone.html | 35.8 kB | | a8a538e5 |
| training_vision_backbone.md | 8.7 kB | | a5183a6a |
| translation.html | 54 kB | | 1946f2ab |
| translation.md | 10.4 kB | | c4ca1a9a |
| video_classification.html | 89.3 kB | | b11d2f3e |
| video_classification.md | 20.8 kB | | 4842e546 |
| video_text_to_text.html | 25.1 kB | | 00b26098 |
| video_text_to_text.md | 6.01 kB | | 1275d694 |
| visual_document_retrieval.html | 26.9 kB | | 500d9b5d |
| visual_document_retrieval.md | 5.68 kB | | ac0cefd1 |
| visual_question_answering.html | 69.7 kB | | 06c1034a |
| visual_question_answering.md | 14.8 kB | | 7fa16c37 |
| zero_shot_image_classification.html | 29.6 kB | | 6f2d3bdc |
| zero_shot_image_classification.md | 5.05 kB | | a3447dd7 |
| zero_shot_object_detection.html | 57.3 kB | | 0b8fe36a |
| zero_shot_object_detection.md | 10.4 kB | | 5b546fe5 |