| any_to_any.html | 26.9 kB | | 0423587e |
| any_to_any.md | 4.85 kB | | 2e35ab4c |
| asr.html | 71.4 kB | | 985598db |
| asr.md | 14.9 kB | | 92ea92c8 |
| audio_classification.html | 65 kB | | 48239ddb |
| audio_classification.md | 12.3 kB | | 9f028fba |
| audio_text_to_text.html | 69.7 kB | | dc3920d0 |
| audio_text_to_text.md | 12.7 kB | | ab9a1174 |
| document_question_answering.html | 108 kB | | cecd70b2 |
| document_question_answering.md | 24.1 kB | | 4148cd6b |
| image_captioning.html | 49.3 kB | | d55226c7 |
| image_captioning.md | 7.39 kB | | 25a12fcf |
| image_classification.html | 60.7 kB | | 3fd6f2b0 |
| image_classification.md | 10.9 kB | | 84760df7 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 53fa5aac |
| image_text_to_text.md | 16.7 kB | | 91f48c74 |
| instance_segmentation.html | 74.1 kB | | 33891856 |
| instance_segmentation.md | 18 kB | | cc0a102b |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 1f6dc690 |
| keypoint_matching.md | 4.4 kB | | 2fd57825 |
| 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 | | 06b67927 |
| language_modeling.md | 14 kB | | 8da98670 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | ed691a03 |
| masked_language_modeling.md | 13.6 kB | | 7c733c8b |
| monocular_depth_estimation.html | 29.4 kB | | 5fb4536b |
| monocular_depth_estimation.md | 5.78 kB | | 83e90844 |
| multiple_choice.html | 51.3 kB | | 82be7ef4 |
| multiple_choice.md | 9.41 kB | | a0e49d33 |
| object_detection.html | 91.9 kB | | 5972a2d0 |
| object_detection.md | 22.8 kB | | 869ffa3e |
| prompting.html | 37.1 kB | | 1b4b4aef |
| prompting.md | 13.4 kB | | dc8e3143 |
| question_answering.html | 54.6 kB | | 66565cec |
| question_answering.md | 11.3 kB | | 05b2e6d8 |
| semantic_segmentation.html | 107 kB | | fcb6975a |
| semantic_segmentation.md | 21.3 kB | | e1f48c05 |
| sequence_classification.html | 53.7 kB | | 131c5139 |
| sequence_classification.md | 10.3 kB | | eeb21b0e |
| summarization.html | 60.2 kB | | 6ab0dfb8 |
| summarization.md | 17.7 kB | | a1ed28cd |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | e93ac5b3 |
| token_classification.md | 13.9 kB | | 3fd0a925 |
| training_vision_backbone.html | 35.8 kB | | eba00f66 |
| training_vision_backbone.md | 8.7 kB | | bf405c78 |
| translation.html | 54 kB | | 0ed3ff15 |
| translation.md | 10.4 kB | | 94ce1e0f |
| video_classification.html | 89.3 kB | | 3a84b4a5 |
| video_classification.md | 20.8 kB | | 2c19ca39 |
| video_text_to_text.html | 25.1 kB | | 6a2153e8 |
| video_text_to_text.md | 6.01 kB | | 07385620 |
| visual_document_retrieval.html | 26.9 kB | | 33dbb35c |
| visual_document_retrieval.md | 5.68 kB | | 29bd2d81 |
| visual_question_answering.html | 69.7 kB | | da733eb9 |
| visual_question_answering.md | 14.8 kB | | 826062b6 |
| zero_shot_image_classification.html | 29.6 kB | | cd968fd7 |
| zero_shot_image_classification.md | 5.05 kB | | 9d406e94 |
| zero_shot_object_detection.html | 57.3 kB | | 4bd35577 |
| zero_shot_object_detection.md | 10.4 kB | | a210e4c6 |