| any_to_any.html | 26.9 kB | | e9aab2d3 |
| any_to_any.md | 4.85 kB | | cf9ed86a |
| asr.html | 71.4 kB | | 72aab699 |
| asr.md | 14.9 kB | | 9d7c9ff0 |
| audio_classification.html | 65 kB | | 56eb653a |
| audio_classification.md | 12.3 kB | | 3b5b1182 |
| audio_text_to_text.html | 69.7 kB | | 2abb5e67 |
| audio_text_to_text.md | 12.7 kB | | 48f397fa |
| document_question_answering.html | 108 kB | | 77e0beac |
| document_question_answering.md | 24.1 kB | | d0161ba1 |
| image_captioning.html | 49.3 kB | | 30312d00 |
| image_captioning.md | 7.39 kB | | 3c0054b2 |
| image_classification.html | 60.7 kB | | 20ed702b |
| image_classification.md | 10.9 kB | | 5ece63a5 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | c7592e3f |
| image_text_to_text.md | 17.1 kB | | bd926583 |
| instance_segmentation.html | 74.1 kB | | 451c8487 |
| instance_segmentation.md | 18 kB | | df0bfc96 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 167eaaa2 |
| keypoint_matching.md | 4.4 kB | | f1bb6537 |
| 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 | | c8b59439 |
| language_modeling.md | 14 kB | | 5ac27c68 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | b992396e |
| masked_language_modeling.md | 13.6 kB | | a50344d9 |
| monocular_depth_estimation.html | 29.4 kB | | 2d13202b |
| monocular_depth_estimation.md | 5.78 kB | | 9149b671 |
| multiple_choice.html | 51.3 kB | | 9fd248e7 |
| multiple_choice.md | 9.41 kB | | 4e29e21b |
| object_detection.html | 91.9 kB | | c90662a1 |
| object_detection.md | 22.8 kB | | f90dec62 |
| prompting.html | 37.1 kB | | 06a25006 |
| prompting.md | 13.4 kB | | 467fbbfb |
| question_answering.html | 54.6 kB | | 99805a43 |
| question_answering.md | 11.3 kB | | bfa4fbc0 |
| semantic_segmentation.html | 107 kB | | e6c245c1 |
| semantic_segmentation.md | 21.3 kB | | f77faa00 |
| sequence_classification.html | 53.8 kB | | 8b6d1e8e |
| sequence_classification.md | 10.3 kB | | e9945f7f |
| summarization.html | 60.2 kB | | cdcc6c89 |
| summarization.md | 17.7 kB | | e0fb2824 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 5f26f92e |
| token_classification.md | 13.9 kB | | be177dec |
| training_vision_backbone.html | 35.8 kB | | 0dd6689f |
| training_vision_backbone.md | 8.7 kB | | 1c81308a |
| translation.html | 54 kB | | e803ce49 |
| translation.md | 10.4 kB | | d5833442 |
| video_classification.html | 89.3 kB | | c574fc47 |
| video_classification.md | 20.8 kB | | 29883fc1 |
| video_text_to_text.html | 25.1 kB | | ca5c366d |
| video_text_to_text.md | 6.01 kB | | d686cb6d |
| visual_document_retrieval.html | 26.9 kB | | cb6e6680 |
| visual_document_retrieval.md | 5.68 kB | | 3c0dc055 |
| visual_question_answering.html | 69.7 kB | | b84dea28 |
| visual_question_answering.md | 14.8 kB | | e2d5964d |
| zero_shot_image_classification.html | 29.6 kB | | ae8d305a |
| zero_shot_image_classification.md | 5.05 kB | | aa5cfbcf |
| zero_shot_object_detection.html | 57.3 kB | | df896391 |
| zero_shot_object_detection.md | 10.4 kB | | b53302b3 |