| any_to_any.html | 27 kB | | bf13c276 |
| any_to_any.md | 4.85 kB | | 9f4dcb82 |
| asr.html | 71.5 kB | | e2760a37 |
| asr.md | 14.9 kB | | 3744ae5d |
| audio_classification.html | 65.1 kB | | 9ba11f08 |
| audio_classification.md | 12.3 kB | | ee1aee55 |
| audio_text_to_text.html | 69.9 kB | | 60e61344 |
| audio_text_to_text.md | 12.7 kB | | b3d095ea |
| document_question_answering.html | 108 kB | | b6a0b159 |
| document_question_answering.md | 24.1 kB | | 79180722 |
| image_captioning.html | 49.5 kB | | a8c94ba0 |
| image_captioning.md | 7.39 kB | | b30474d1 |
| image_classification.html | 60.9 kB | | 76c42f02 |
| image_classification.md | 10.9 kB | | 465bb7ef |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | a05acc06 |
| image_text_to_text.md | 17.1 kB | | 00d09706 |
| instance_segmentation.html | 74.3 kB | | 5ba11fb7 |
| instance_segmentation.md | 18 kB | | 4eb4436b |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 56035eae |
| keypoint_matching.md | 4.4 kB | | f8bb1622 |
| 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 | | 56f17108 |
| language_modeling.md | 14 kB | | d7039276 |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 84f7b771 |
| masked_language_modeling.md | 13.6 kB | | b78a82c3 |
| monocular_depth_estimation.html | 29.5 kB | | e10cdb39 |
| monocular_depth_estimation.md | 5.78 kB | | 4a0ce766 |
| multiple_choice.html | 51.4 kB | | e6622933 |
| multiple_choice.md | 9.41 kB | | 3e9b164e |
| object_detection.html | 92 kB | | 378f4e42 |
| object_detection.md | 22.8 kB | | 10137c91 |
| prompting.html | 45.6 kB | | 380543ca |
| prompting.md | 13.4 kB | | efc297c3 |
| question_answering.html | 54.8 kB | | 8ad61eb9 |
| question_answering.md | 11.3 kB | | 626c8252 |
| semantic_segmentation.html | 107 kB | | f0726868 |
| semantic_segmentation.md | 21.3 kB | | dbe85d67 |
| sequence_classification.html | 53.9 kB | | edb667c8 |
| sequence_classification.md | 10.3 kB | | eaa2b2bf |
| summarization.html | 60.4 kB | | 0b4dd31e |
| summarization.md | 17.7 kB | | 044b95c7 |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 146f76ee |
| token_classification.md | 13.9 kB | | 424f6209 |
| training_vision_backbone.html | 35.9 kB | | 308ab97d |
| training_vision_backbone.md | 8.7 kB | | 204e55bf |
| translation.html | 54.2 kB | | 555459ca |
| translation.md | 10.4 kB | | 7abe871e |
| video_classification.html | 89.5 kB | | 3c2598e4 |
| video_classification.md | 20.8 kB | | 3db2d92a |
| video_text_to_text.html | 25.2 kB | | 4a2e80c2 |
| video_text_to_text.md | 6.01 kB | | 1e9b0677 |
| visual_document_retrieval.html | 27 kB | | 0e63dc85 |
| visual_document_retrieval.md | 5.68 kB | | 9a746123 |
| visual_question_answering.html | 69.9 kB | | 677eaeb1 |
| visual_question_answering.md | 14.8 kB | | 4b32930b |
| zero_shot_image_classification.html | 29.7 kB | | 30fa99a7 |
| zero_shot_image_classification.md | 5.05 kB | | 0d18624e |
| zero_shot_object_detection.html | 57.4 kB | | 04a941f1 |
| zero_shot_object_detection.md | 10.4 kB | | 69992dca |