| any_to_any.html | 26.9 kB | | 694c3e97 |
| any_to_any.md | 4.85 kB | | 9ca88037 |
| asr.html | 71.4 kB | | 62ad1104 |
| asr.md | 14.9 kB | | dd3bb1ad |
| audio_classification.html | 65 kB | | 593acefe |
| audio_classification.md | 12.3 kB | | a5e4afa7 |
| audio_text_to_text.html | 69.6 kB | | fa9dda0f |
| audio_text_to_text.md | 12.7 kB | | b962953f |
| document_question_answering.html | 108 kB | | 8ed3e659 |
| document_question_answering.md | 24.1 kB | | ff05ce0a |
| image_captioning.html | 49.3 kB | | c5c9ddb5 |
| image_captioning.md | 7.39 kB | | b63a68d8 |
| image_classification.html | 60.7 kB | | 177bbed0 |
| image_classification.md | 10.9 kB | | e193f45b |
| image_feature_extraction.html | 30.4 kB | | c49077ee |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | a907cf1c |
| image_text_to_text.md | 16.7 kB | | 1a9f666c |
| instance_segmentation.html | 74.1 kB | | aaa4ea83 |
| instance_segmentation.md | 18 kB | | a0623308 |
| keypoint_detection.html | 25.9 kB | | 9df40b44 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | d1fcee0f |
| keypoint_matching.md | 4.4 kB | | 4e344d18 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 18647377 |
| knowledge_distillation_for_image_classification.md | 7.74 kB | | f7c4bfaf |
| language_modeling.html | 62.4 kB | | 16878158 |
| language_modeling.md | 14 kB | | c11d7df6 |
| mask_generation.html | 79.9 kB | | 139067ce |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 6abbae76 |
| masked_language_modeling.md | 13.6 kB | | 38fb910d |
| monocular_depth_estimation.html | 29.4 kB | | 06ddd99b |
| monocular_depth_estimation.md | 5.78 kB | | 6d5f91dd |
| multiple_choice.html | 51.2 kB | | 27437eb7 |
| multiple_choice.md | 9.39 kB | | ae72687e |
| object_detection.html | 91.9 kB | | bf1e1ff8 |
| object_detection.md | 22.8 kB | | abef868f |
| prompting.html | 37.1 kB | | b6f4d791 |
| prompting.md | 13.4 kB | | 87c6e7e9 |
| question_answering.html | 54.4 kB | | 6d9aac14 |
| question_answering.md | 11.3 kB | | a5b97582 |
| semantic_segmentation.html | 114 kB | | 771ef0fb |
| semantic_segmentation.md | 23.6 kB | | 10e39cf6 |
| sequence_classification.html | 53.7 kB | | f92fb879 |
| sequence_classification.md | 10.3 kB | | 91559467 |
| summarization.html | 60.2 kB | | 8aa2566c |
| summarization.md | 17.7 kB | | 27e6a0b9 |
| text-to-speech.html | 127 kB | | caccb307 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 72.9 kB | | 07f0966e |
| token_classification.md | 13.8 kB | | 9d5df343 |
| training_vision_backbone.html | 35.8 kB | | 60d525fe |
| training_vision_backbone.md | 8.7 kB | | 3cb4e8f5 |
| translation.html | 54 kB | | e3a270b5 |
| translation.md | 10.3 kB | | 9810f62b |
| video_classification.html | 89.3 kB | | c54adea8 |
| video_classification.md | 20.8 kB | | 332fed34 |
| video_text_to_text.html | 25.1 kB | | 32aecb76 |
| video_text_to_text.md | 6.01 kB | | abc46cfa |
| visual_document_retrieval.html | 26.9 kB | | f3fd359a |
| visual_document_retrieval.md | 5.68 kB | | e2ac1822 |
| visual_question_answering.html | 69.7 kB | | 85d76b4c |
| visual_question_answering.md | 14.8 kB | | 5a58c042 |
| zero_shot_image_classification.html | 29.6 kB | | 6f6fbe61 |
| zero_shot_image_classification.md | 5.05 kB | | 82c889f1 |
| zero_shot_object_detection.html | 57.3 kB | | 6140e80f |
| zero_shot_object_detection.md | 10.4 kB | | 65bccdbf |
