| any_to_any.html | 26.9 kB | | 4040f13f |
| any_to_any.md | 4.85 kB | | 2b0d15a6 |
| asr.html | 71.4 kB | | 3a605d14 |
| asr.md | 14.9 kB | | 2e111a1f |
| audio_classification.html | 65 kB | | 22b6632a |
| audio_classification.md | 12.3 kB | | 8eacab67 |
| audio_text_to_text.html | 69.4 kB | | b037dee1 |
| audio_text_to_text.md | 12.5 kB | | bd466bd4 |
| document_question_answering.html | 108 kB | | 64ebbf5e |
| document_question_answering.md | 24.1 kB | | 82ed3ccc |
| image_captioning.html | 49.3 kB | | fe54aa3d |
| image_captioning.md | 7.39 kB | | 114a5726 |
| image_classification.html | 60.8 kB | | 7f43f55b |
| image_classification.md | 10.9 kB | | 2ffbba4d |
| image_feature_extraction.html | 30.4 kB | | c49077ee |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 60.7 kB | | 1f427882 |
| image_text_to_text.md | 16.6 kB | | 5f659cbf |
| instance_segmentation.html | 74.1 kB | | 3010f2c4 |
| instance_segmentation.md | 18 kB | | 2582c7f7 |
| keypoint_detection.html | 25.9 kB | | 9df40b44 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 716e2e66 |
| keypoint_matching.md | 4.4 kB | | 613630ae |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 761fead5 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 7e97937b |
| language_modeling.html | 62.4 kB | | 507ae34a |
| language_modeling.md | 14 kB | | 342d253a |
| mask_generation.html | 79.9 kB | | 139067ce |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | e14def6c |
| masked_language_modeling.md | 13.6 kB | | 001e542d |
| monocular_depth_estimation.html | 29.5 kB | | 196a15a1 |
| monocular_depth_estimation.md | 5.82 kB | | a50e036d |
| multiple_choice.html | 51.3 kB | | f9094f60 |
| multiple_choice.md | 9.42 kB | | 87aa2821 |
| object_detection.html | 91.9 kB | | 233f7c6a |
| object_detection.md | 22.8 kB | | 1af74979 |
| prompting.html | 37 kB | | 468c7a38 |
| prompting.md | 13.4 kB | | 4d55da1c |
| question_answering.html | 54.7 kB | | 4489643b |
| question_answering.md | 11.4 kB | | ebd52826 |
| semantic_segmentation.html | 114 kB | | 20552da7 |
| semantic_segmentation.md | 23.7 kB | | d8b32994 |
| sequence_classification.html | 53.7 kB | | dad19b84 |
| sequence_classification.md | 10.4 kB | | 48e65d06 |
| summarization.html | 60.2 kB | | 182aa1fb |
| summarization.md | 17.7 kB | | 89db0b9d |
| text-to-speech.html | 127 kB | | caccb307 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 7c43cff3 |
| token_classification.md | 13.9 kB | | dfb075c5 |
| training_vision_backbone.html | 35.8 kB | | d8553134 |
| training_vision_backbone.md | 8.7 kB | | 422d8750 |
| translation.html | 54 kB | | 7c64ebf5 |
| translation.md | 10.4 kB | | 25f23f0d |
| video_classification.html | 89.4 kB | | d85b3a4f |
| video_classification.md | 20.8 kB | | b27caa2f |
| video_text_to_text.html | 25.1 kB | | e1fd4509 |
| video_text_to_text.md | 6.01 kB | | 71e6f843 |
| visual_document_retrieval.html | 26.9 kB | | 21c69f9a |
| visual_document_retrieval.md | 5.68 kB | | 6ae8007d |
| visual_question_answering.html | 69.7 kB | | 2918545c |
| visual_question_answering.md | 14.8 kB | | c862f333 |
| zero_shot_image_classification.html | 29.6 kB | | 1fd0ef77 |
| zero_shot_image_classification.md | 5.05 kB | | 39cce7cc |
| zero_shot_object_detection.html | 57.3 kB | | 053e009c |
| zero_shot_object_detection.md | 10.4 kB | | 496e7a3a |
