| any_to_any.html | 26.9 kB | | b1051382 |
| any_to_any.md | 4.85 kB | | 89f990a2 |
| asr.html | 71.4 kB | | f6f15026 |
| asr.md | 14.9 kB | | a68170ca |
| audio_classification.html | 65 kB | | 500faeed |
| audio_classification.md | 12.3 kB | | 72af6e92 |
| audio_text_to_text.html | 69.7 kB | | 99cb3de2 |
| audio_text_to_text.md | 12.7 kB | | 07ad9c58 |
| document_question_answering.html | 108 kB | | 2e7ea64c |
| document_question_answering.md | 24.1 kB | | ba7fed5a |
| image_captioning.html | 49.3 kB | | 41ee6c0f |
| image_captioning.md | 7.39 kB | | 5e489073 |
| image_classification.html | 60.7 kB | | e600dee1 |
| image_classification.md | 10.9 kB | | 6d8c6e4f |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 4bfef6bb |
| image_text_to_text.md | 16.7 kB | | ef17a23e |
| instance_segmentation.html | 74.1 kB | | c59492ba |
| instance_segmentation.md | 18 kB | | 1d9932ab |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 9601d111 |
| keypoint_matching.md | 4.4 kB | | eab6bda2 |
| 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 | | fa04eb99 |
| language_modeling.md | 14 kB | | d09b4939 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 791832eb |
| masked_language_modeling.md | 13.6 kB | | d4ba63f9 |
| monocular_depth_estimation.html | 29.4 kB | | 57866df8 |
| monocular_depth_estimation.md | 5.78 kB | | 6a64f002 |
| multiple_choice.html | 51.3 kB | | 7e6b3d56 |
| multiple_choice.md | 9.41 kB | | 5519e710 |
| object_detection.html | 91.9 kB | | bfdd7e4b |
| object_detection.md | 22.8 kB | | 953277ee |
| prompting.html | 37.1 kB | | 2c5a0790 |
| prompting.md | 13.4 kB | | d0a7da41 |
| question_answering.html | 54.6 kB | | 4cb8c1e4 |
| question_answering.md | 11.3 kB | | 47811780 |
| semantic_segmentation.html | 114 kB | | b0d302fa |
| semantic_segmentation.md | 23.6 kB | | 45af8a45 |
| sequence_classification.html | 53.7 kB | | 6e9d7727 |
| sequence_classification.md | 10.3 kB | | 86ce0e2d |
| summarization.html | 60.2 kB | | c36a0fb0 |
| summarization.md | 17.7 kB | | f693f89a |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | c2fc386c |
| token_classification.md | 13.9 kB | | aac6ec81 |
| training_vision_backbone.html | 35.8 kB | | 86a1ce42 |
| training_vision_backbone.md | 8.7 kB | | 7dd23791 |
| translation.html | 54 kB | | 58228a26 |
| translation.md | 10.4 kB | | 80a0dd1a |
| video_classification.html | 89.3 kB | | 5e1c3a45 |
| video_classification.md | 20.8 kB | | 0c006a0c |
| video_text_to_text.html | 25.1 kB | | 8769a6cb |
| video_text_to_text.md | 6.01 kB | | 4c5eb76e |
| visual_document_retrieval.html | 26.9 kB | | a210bacd |
| visual_document_retrieval.md | 5.68 kB | | 882aaa04 |
| visual_question_answering.html | 69.7 kB | | f02bd165 |
| visual_question_answering.md | 14.8 kB | | d9503154 |
| zero_shot_image_classification.html | 29.6 kB | | 5665a4b2 |
| zero_shot_image_classification.md | 5.05 kB | | b36436ca |
| zero_shot_object_detection.html | 57.3 kB | | 4512b250 |
| zero_shot_object_detection.md | 10.4 kB | | 007b5a01 |