| any_to_any.html | 27.1 kB | | 4e137454 |
| any_to_any.md | 4.85 kB | | ea358404 |
| asr.html | 71.6 kB | | 36b0d87c |
| asr.md | 14.9 kB | | 42e4b542 |
| audio_classification.html | 65.2 kB | | e276efba |
| audio_classification.md | 12.3 kB | | 2235c1bd |
| audio_text_to_text.html | 70 kB | | 9845c798 |
| audio_text_to_text.md | 12.7 kB | | 74ef3757 |
| document_question_answering.html | 108 kB | | f0bfb009 |
| document_question_answering.md | 24.1 kB | | 3636768f |
| image_captioning.html | 49.6 kB | | e0a8377b |
| image_captioning.md | 7.39 kB | | d6505a97 |
| image_classification.html | 60.9 kB | | 86ea2735 |
| image_classification.md | 10.9 kB | | 44709054 |
| image_feature_extraction.html | 30.6 kB | | ae7de98b |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | d30a96cf |
| image_text_to_text.md | 17.1 kB | | 98f2b1fe |
| instance_segmentation.html | 74.3 kB | | 4feed557 |
| instance_segmentation.md | 18 kB | | 3e1204e7 |
| keypoint_detection.html | 26 kB | | 205b73f4 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.8 kB | | b6f06b8f |
| keypoint_matching.md | 4.4 kB | | 10557d0b |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | 97024292 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.6 kB | | 0d36a95e |
| language_modeling.md | 14 kB | | 16756a50 |
| mask_generation.html | 80 kB | | 392fead7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.5 kB | | 73a04ff9 |
| masked_language_modeling.md | 13.6 kB | | 3768ace0 |
| monocular_depth_estimation.html | 29.5 kB | | d6323089 |
| monocular_depth_estimation.md | 5.78 kB | | d4e00a4c |
| multiple_choice.html | 51.5 kB | | 13edfc12 |
| multiple_choice.md | 9.41 kB | | 36392b9e |
| object_detection.html | 92.1 kB | | 730f0833 |
| object_detection.md | 22.8 kB | | 391835e2 |
| prompting.html | 45.7 kB | | c7a1bce3 |
| prompting.md | 13.4 kB | | 775d863d |
| question_answering.html | 54.8 kB | | 5d14668c |
| question_answering.md | 11.3 kB | | 69de6a1f |
| semantic_segmentation.html | 107 kB | | 1a7f5f62 |
| semantic_segmentation.md | 21.3 kB | | 3d4345cd |
| sequence_classification.html | 54 kB | | d3a6af4c |
| sequence_classification.md | 10.3 kB | | 025b1b7e |
| summarization.html | 60.4 kB | | 791baee4 |
| summarization.md | 17.7 kB | | c729e474 |
| text-to-speech.html | 127 kB | | 40c6298e |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.2 kB | | 5ec528f3 |
| token_classification.md | 13.9 kB | | 9c07da19 |
| training_vision_backbone.html | 36 kB | | f7f532c0 |
| training_vision_backbone.md | 8.7 kB | | 9216a901 |
| translation.html | 54.2 kB | | 8ec2158f |
| translation.md | 10.4 kB | | 89e4b4f3 |
| video_classification.html | 89.5 kB | | 8b9753aa |
| video_classification.md | 20.8 kB | | 27e11478 |
| video_text_to_text.html | 25.3 kB | | f04b1419 |
| video_text_to_text.md | 6.01 kB | | 1d415ed5 |
| visual_document_retrieval.html | 27 kB | | d0c8611a |
| visual_document_retrieval.md | 5.68 kB | | 824edf95 |
| visual_question_answering.html | 70 kB | | faa556f1 |
| visual_question_answering.md | 14.8 kB | | 5b70818d |
| zero_shot_image_classification.html | 29.8 kB | | 043a81d3 |
| zero_shot_image_classification.md | 5.05 kB | | c112996e |
| zero_shot_object_detection.html | 57.5 kB | | 3c0f063b |
| zero_shot_object_detection.md | 10.4 kB | | 60b5f387 |