| any_to_any.html | 26.9 kB | | 4cb2a351 |
| any_to_any.md | 4.85 kB | | 3f65e4ae |
| asr.html | 71.4 kB | | 96e8879f |
| asr.md | 14.9 kB | | 4ad078b7 |
| audio_classification.html | 65 kB | | a24a5f8e |
| audio_classification.md | 12.3 kB | | 612c4c70 |
| audio_text_to_text.html | 69.7 kB | | 8179f813 |
| audio_text_to_text.md | 12.7 kB | | e125c0a3 |
| document_question_answering.html | 108 kB | | 76f1897d |
| document_question_answering.md | 24.1 kB | | 4d180341 |
| image_captioning.html | 49.3 kB | | 7811b6fb |
| image_captioning.md | 7.39 kB | | 4b3619cc |
| image_classification.html | 60.7 kB | | 183b44f5 |
| image_classification.md | 10.9 kB | | 44b52fe9 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 7515b5d1 |
| image_text_to_text.md | 16.7 kB | | f1f25cc6 |
| instance_segmentation.html | 74.1 kB | | 1d833461 |
| instance_segmentation.md | 18 kB | | ec0bd243 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | c3bb1509 |
| keypoint_matching.md | 4.4 kB | | 8159a3ab |
| 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 | | 98ad2398 |
| language_modeling.md | 14 kB | | 6abd026a |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 1473ce71 |
| masked_language_modeling.md | 13.6 kB | | 449fb111 |
| monocular_depth_estimation.html | 29.4 kB | | a680c1a6 |
| monocular_depth_estimation.md | 5.78 kB | | 25d8126c |
| multiple_choice.html | 51.3 kB | | 315a97b7 |
| multiple_choice.md | 9.41 kB | | 34870ec2 |
| object_detection.html | 91.9 kB | | 2d1353c1 |
| object_detection.md | 22.8 kB | | 9739d4b2 |
| prompting.html | 37.1 kB | | 285a39d4 |
| prompting.md | 13.4 kB | | 432b2a05 |
| question_answering.html | 54.6 kB | | 05628b98 |
| question_answering.md | 11.3 kB | | c6f447d0 |
| semantic_segmentation.html | 107 kB | | 6ec79ca1 |
| semantic_segmentation.md | 21.3 kB | | a755137d |
| sequence_classification.html | 53.8 kB | | 18f0279b |
| sequence_classification.md | 10.3 kB | | 7c816daf |
| summarization.html | 60.2 kB | | de009ba6 |
| summarization.md | 17.7 kB | | 3fdc3403 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | f28b42c2 |
| token_classification.md | 13.9 kB | | 608f32d5 |
| training_vision_backbone.html | 35.8 kB | | 1e8e9f11 |
| training_vision_backbone.md | 8.7 kB | | aae2506a |
| translation.html | 54 kB | | 39278eb2 |
| translation.md | 10.4 kB | | 6e8c4a56 |
| video_classification.html | 89.3 kB | | 5e22142d |
| video_classification.md | 20.8 kB | | 1150c9e9 |
| video_text_to_text.html | 25.1 kB | | d5032c91 |
| video_text_to_text.md | 6.01 kB | | b275aa8d |
| visual_document_retrieval.html | 26.9 kB | | 0e5f8c94 |
| visual_document_retrieval.md | 5.68 kB | | b88cba45 |
| visual_question_answering.html | 69.7 kB | | 8bba2d57 |
| visual_question_answering.md | 14.8 kB | | 3567fd67 |
| zero_shot_image_classification.html | 29.6 kB | | a255b8fb |
| zero_shot_image_classification.md | 5.05 kB | | d3aec9e1 |
| zero_shot_object_detection.html | 57.3 kB | | c836d5f9 |
| zero_shot_object_detection.md | 10.4 kB | | 37867fcc |