| any_to_any.html | 26.9 kB | | 181b0b3e |
| any_to_any.md | 4.85 kB | | f1922428 |
| asr.html | 71.4 kB | | 3fd4a680 |
| asr.md | 14.9 kB | | deaa91b1 |
| audio_classification.html | 65 kB | | 0b07ab94 |
| audio_classification.md | 12.3 kB | | 849456c6 |
| audio_text_to_text.html | 69.7 kB | | 0e86e641 |
| audio_text_to_text.md | 12.7 kB | | 89d9df14 |
| document_question_answering.html | 108 kB | | e9d1250c |
| document_question_answering.md | 24.1 kB | | db08b832 |
| image_captioning.html | 49.3 kB | | ebf447bf |
| image_captioning.md | 7.39 kB | | 44513fde |
| image_classification.html | 60.7 kB | | cddb7560 |
| image_classification.md | 10.9 kB | | 52bedb5e |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.1 kB | | c625e294 |
| image_text_to_text.md | 17.1 kB | | a7228561 |
| instance_segmentation.html | 74.1 kB | | a07e6d92 |
| instance_segmentation.md | 18 kB | | cf07545b |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 945f1552 |
| keypoint_matching.md | 4.4 kB | | 0e1ba757 |
| 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 | | d2656d97 |
| language_modeling.md | 14 kB | | 52e7da57 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 4b610d44 |
| masked_language_modeling.md | 13.6 kB | | de854014 |
| monocular_depth_estimation.html | 29.4 kB | | 80f27c93 |
| monocular_depth_estimation.md | 5.78 kB | | 9131d2b0 |
| multiple_choice.html | 51.3 kB | | 7f129355 |
| multiple_choice.md | 9.41 kB | | 6d1b174b |
| object_detection.html | 91.9 kB | | 7226ef67 |
| object_detection.md | 22.8 kB | | a700e026 |
| prompting.html | 37.1 kB | | 5d2ea1d0 |
| prompting.md | 13.4 kB | | f85c415b |
| question_answering.html | 54.6 kB | | 8abb652f |
| question_answering.md | 11.3 kB | | 43596f95 |
| semantic_segmentation.html | 107 kB | | bc595e00 |
| semantic_segmentation.md | 21.3 kB | | 750c6a8e |
| sequence_classification.html | 53.8 kB | | 42e8e101 |
| sequence_classification.md | 10.3 kB | | b08d082b |
| summarization.html | 60.2 kB | | 9a94bcb3 |
| summarization.md | 17.7 kB | | faba0592 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 69f59a9f |
| token_classification.md | 13.9 kB | | 7379108c |
| training_vision_backbone.html | 35.8 kB | | 1210a7ac |
| training_vision_backbone.md | 8.7 kB | | 9a3a617e |
| translation.html | 54 kB | | a1e32b0a |
| translation.md | 10.4 kB | | 4fcdae5c |
| video_classification.html | 89.3 kB | | fdab3294 |
| video_classification.md | 20.8 kB | | ef9d6d52 |
| video_text_to_text.html | 25.1 kB | | 3d5790b2 |
| video_text_to_text.md | 6.01 kB | | 0567610e |
| visual_document_retrieval.html | 26.9 kB | | c97353e9 |
| visual_document_retrieval.md | 5.68 kB | | a09a647b |
| visual_question_answering.html | 69.8 kB | | b115ec45 |
| visual_question_answering.md | 14.8 kB | | 370b9a45 |
| zero_shot_image_classification.html | 29.6 kB | | f4eaf4a7 |
| zero_shot_image_classification.md | 5.05 kB | | 062c71cf |
| zero_shot_object_detection.html | 57.3 kB | | 614c6f1b |
| zero_shot_object_detection.md | 10.4 kB | | 2d7137ed |