| any_to_any.html | 26.9 kB | | 5cc4269d |
| any_to_any.md | 4.85 kB | | 9fc454ae |
| asr.html | 71.4 kB | | db0071c7 |
| asr.md | 14.9 kB | | 5ff5baf9 |
| audio_classification.html | 65 kB | | 261bfa6c |
| audio_classification.md | 12.3 kB | | 827b91b4 |
| audio_text_to_text.html | 69.7 kB | | 9c6dba47 |
| audio_text_to_text.md | 12.7 kB | | 3f641fd9 |
| document_question_answering.html | 108 kB | | a3fd88b5 |
| document_question_answering.md | 24.1 kB | | 4480c826 |
| image_captioning.html | 49.3 kB | | b2acb33f |
| image_captioning.md | 7.39 kB | | 7c8380d3 |
| image_classification.html | 60.7 kB | | c60f9a23 |
| image_classification.md | 10.9 kB | | 9c9224e7 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 260adb60 |
| image_text_to_text.md | 17.1 kB | | 234acc96 |
| instance_segmentation.html | 74.1 kB | | e448b15a |
| instance_segmentation.md | 18 kB | | 6863a0c8 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 5f3d50a9 |
| keypoint_matching.md | 4.4 kB | | 834009c7 |
| 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 | | 18b7e484 |
| language_modeling.md | 14 kB | | 8d6e9cb4 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | afb4d84e |
| masked_language_modeling.md | 13.6 kB | | ee432ee5 |
| monocular_depth_estimation.html | 29.4 kB | | 0e2e9897 |
| monocular_depth_estimation.md | 5.78 kB | | e1d8174c |
| multiple_choice.html | 51.3 kB | | c5050aa3 |
| multiple_choice.md | 9.41 kB | | 1dccb246 |
| object_detection.html | 91.9 kB | | d5eb466c |
| object_detection.md | 22.8 kB | | b20105b4 |
| prompting.html | 37.1 kB | | 2f33d090 |
| prompting.md | 13.4 kB | | c4661de1 |
| question_answering.html | 54.6 kB | | 4030b67e |
| question_answering.md | 11.3 kB | | ae9ae9c7 |
| semantic_segmentation.html | 107 kB | | e7986faf |
| semantic_segmentation.md | 21.3 kB | | dd60aee7 |
| sequence_classification.html | 53.8 kB | | 68f7ffa3 |
| sequence_classification.md | 10.3 kB | | b7ebd5dc |
| summarization.html | 60.2 kB | | 92c3cc3c |
| summarization.md | 17.7 kB | | 4d11fce2 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 0c8f13b9 |
| token_classification.md | 13.9 kB | | 3cde66ae |
| training_vision_backbone.html | 35.8 kB | | 76a0d1e9 |
| training_vision_backbone.md | 8.7 kB | | 4cc6e844 |
| translation.html | 54 kB | | 7af2833f |
| translation.md | 10.4 kB | | 5b05974b |
| video_classification.html | 89.3 kB | | d58f9136 |
| video_classification.md | 20.8 kB | | 857bca30 |
| video_text_to_text.html | 25.1 kB | | 3b53046d |
| video_text_to_text.md | 6.01 kB | | 625161a0 |
| visual_document_retrieval.html | 26.9 kB | | c8a4a3b2 |
| visual_document_retrieval.md | 5.68 kB | | 26de6220 |
| visual_question_answering.html | 69.7 kB | | 094183b1 |
| visual_question_answering.md | 14.8 kB | | cddb998d |
| zero_shot_image_classification.html | 29.6 kB | | 3c6ac949 |
| zero_shot_image_classification.md | 5.05 kB | | 2136ae76 |
| zero_shot_object_detection.html | 57.3 kB | | 89cf8bff |
| zero_shot_object_detection.md | 10.4 kB | | 34fd83d8 |