| any_to_any.html | 26.9 kB | | 419c1887 |
| any_to_any.md | 4.85 kB | | 8698b29e |
| asr.html | 71.4 kB | | 424ac8ec |
| asr.md | 14.9 kB | | 3a33978a |
| audio_classification.html | 65 kB | | 8bf3964a |
| audio_classification.md | 12.3 kB | | 47c4cdb4 |
| audio_text_to_text.html | 69.7 kB | | d59404de |
| audio_text_to_text.md | 12.7 kB | | 4ff79e4d |
| document_question_answering.html | 108 kB | | a4971fdf |
| document_question_answering.md | 24.1 kB | | fbf5f265 |
| image_captioning.html | 49.3 kB | | 3bcca7c1 |
| image_captioning.md | 7.39 kB | | ba8d5ed0 |
| image_classification.html | 60.7 kB | | c4470ebf |
| image_classification.md | 10.9 kB | | 6edb8c9b |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 2c0165ea |
| image_text_to_text.md | 17.1 kB | | c07a5cbd |
| instance_segmentation.html | 74.1 kB | | a3c4b150 |
| instance_segmentation.md | 18 kB | | d7dc42ef |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | ae5fcd6d |
| keypoint_matching.md | 4.4 kB | | 9c9ce619 |
| 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 | | ca90483b |
| language_modeling.md | 14 kB | | 63ac7235 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | c9ed36c2 |
| masked_language_modeling.md | 13.6 kB | | cd49b53a |
| monocular_depth_estimation.html | 29.4 kB | | 8bc226b4 |
| monocular_depth_estimation.md | 5.78 kB | | 81c2993c |
| multiple_choice.html | 51.3 kB | | 15b9408c |
| multiple_choice.md | 9.41 kB | | 88964f92 |
| object_detection.html | 91.9 kB | | 86b3d558 |
| object_detection.md | 22.8 kB | | 42246364 |
| prompting.html | 37.1 kB | | ca853c69 |
| prompting.md | 13.4 kB | | 8ecef520 |
| question_answering.html | 54.6 kB | | 55caf246 |
| question_answering.md | 11.3 kB | | f69785a4 |
| semantic_segmentation.html | 107 kB | | 9b5d3147 |
| semantic_segmentation.md | 21.3 kB | | dd2e1b00 |
| sequence_classification.html | 53.8 kB | | 20b9fef1 |
| sequence_classification.md | 10.3 kB | | 03ea0437 |
| summarization.html | 60.2 kB | | e381f5d0 |
| summarization.md | 17.7 kB | | cfc77694 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 45ff87ff |
| token_classification.md | 13.9 kB | | f7ed0f70 |
| training_vision_backbone.html | 35.8 kB | | 53da8a97 |
| training_vision_backbone.md | 8.7 kB | | 897450b1 |
| translation.html | 54 kB | | 44a43905 |
| translation.md | 10.4 kB | | 92df9e69 |
| video_classification.html | 89.3 kB | | 12c7cf55 |
| video_classification.md | 20.8 kB | | 32ec94f7 |
| video_text_to_text.html | 25.1 kB | | 17cc7ff6 |
| video_text_to_text.md | 6.01 kB | | 1e5f9cc9 |
| visual_document_retrieval.html | 26.9 kB | | d9573d69 |
| visual_document_retrieval.md | 5.68 kB | | 7d667741 |
| visual_question_answering.html | 69.7 kB | | 22de96a3 |
| visual_question_answering.md | 14.8 kB | | 3bbeab19 |
| zero_shot_image_classification.html | 29.6 kB | | b9ec12e5 |
| zero_shot_image_classification.md | 5.05 kB | | 1891fe24 |
| zero_shot_object_detection.html | 57.3 kB | | 3678ad77 |
| zero_shot_object_detection.md | 10.4 kB | | a65b30e6 |