| any_to_any.html | 27 kB | | 43ab256d |
| any_to_any.md | 4.85 kB | | b9ebcd0c |
| asr.html | 71.5 kB | | dba33e52 |
| asr.md | 14.9 kB | | 58d78e04 |
| audio_classification.html | 65.1 kB | | e533160a |
| audio_classification.md | 12.3 kB | | 6a047d24 |
| audio_text_to_text.html | 69.9 kB | | 3e6a42d3 |
| audio_text_to_text.md | 12.7 kB | | e2e132c7 |
| document_question_answering.html | 108 kB | | 45dde940 |
| document_question_answering.md | 24.1 kB | | 6cb1556c |
| image_captioning.html | 49.5 kB | | 9289076f |
| image_captioning.md | 7.39 kB | | 93543bd9 |
| image_classification.html | 60.9 kB | | bd01a8b6 |
| image_classification.md | 10.9 kB | | bd79432d |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.1 kB | | 937342e5 |
| image_text_to_text.md | 17 kB | | 2ace8179 |
| instance_segmentation.html | 74.3 kB | | 94ef550e |
| instance_segmentation.md | 18 kB | | 2e960c5c |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | ba409af8 |
| keypoint_matching.md | 4.4 kB | | 25807688 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | fdde2a8b |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | ee6138bf |
| language_modeling.md | 14 kB | | 52cc35bf |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 9a6a2a97 |
| masked_language_modeling.md | 13.6 kB | | ed4dc882 |
| monocular_depth_estimation.html | 29.5 kB | | 5e5b5ca3 |
| monocular_depth_estimation.md | 5.78 kB | | d7b938b6 |
| multiple_choice.html | 51.4 kB | | e1ee57a7 |
| multiple_choice.md | 9.41 kB | | 9cf3d0b4 |
| object_detection.html | 92 kB | | 8176cf38 |
| object_detection.md | 22.8 kB | | e9308101 |
| prompting.html | 45.6 kB | | 1d56de0d |
| prompting.md | 13.4 kB | | 9a17b796 |
| question_answering.html | 54.8 kB | | 39e1d7f4 |
| question_answering.md | 11.3 kB | | 90b55cbb |
| semantic_segmentation.html | 107 kB | | 51bf6ac5 |
| semantic_segmentation.md | 21.3 kB | | 4d971592 |
| sequence_classification.html | 53.9 kB | | b6786ca8 |
| sequence_classification.md | 10.3 kB | | 2fffd961 |
| summarization.html | 60.4 kB | | 04a1fbd4 |
| summarization.md | 17.7 kB | | ee8413a4 |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 11abf062 |
| token_classification.md | 13.9 kB | | 58956de7 |
| training_vision_backbone.html | 35.9 kB | | 8d4aad61 |
| training_vision_backbone.md | 8.7 kB | | 3df8e626 |
| translation.html | 54.2 kB | | d1f047f0 |
| translation.md | 10.4 kB | | 49b45df4 |
| video_classification.html | 89.2 kB | | 0d79bf7b |
| video_classification.md | 20.6 kB | | 7f28f033 |
| video_text_to_text.html | 25.2 kB | | 3675dd9f |
| video_text_to_text.md | 6.01 kB | | c48c2617 |
| visual_document_retrieval.html | 27 kB | | 79a157b5 |
| visual_document_retrieval.md | 5.68 kB | | b4b33953 |
| visual_question_answering.html | 69.6 kB | | 2ed3acbf |
| visual_question_answering.md | 14.6 kB | | 37c060ea |
| zero_shot_image_classification.html | 29.7 kB | | d6285f51 |
| zero_shot_image_classification.md | 5.05 kB | | 24ccf0b3 |
| zero_shot_object_detection.html | 57.4 kB | | ed046c54 |
| zero_shot_object_detection.md | 10.4 kB | | 59546abb |