| any_to_any.html | 27 kB | | 03114653 |
| any_to_any.md | 4.85 kB | | 6d7b8c92 |
| asr.html | 71.5 kB | | d9294d4f |
| asr.md | 14.9 kB | | 37d10dc7 |
| audio_classification.html | 65.1 kB | | d117f2c4 |
| audio_classification.md | 12.3 kB | | 713f885d |
| audio_text_to_text.html | 69.9 kB | | 11571a4f |
| audio_text_to_text.md | 12.7 kB | | a3f37b89 |
| document_question_answering.html | 108 kB | | 2c5659d5 |
| document_question_answering.md | 24.1 kB | | 6d56d43a |
| image_captioning.html | 49.5 kB | | 2c870aae |
| image_captioning.md | 7.39 kB | | 591f757e |
| image_classification.html | 60.9 kB | | e4e2f65c |
| image_classification.md | 10.9 kB | | 4bd352b9 |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.1 kB | | 4d28d1ff |
| image_text_to_text.md | 17 kB | | 1585661c |
| instance_segmentation.html | 74.3 kB | | 5122b1ca |
| instance_segmentation.md | 18 kB | | 5f9b4280 |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 9a8f5d63 |
| keypoint_matching.md | 4.4 kB | | 832f93ff |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | fdde2a8b |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 831b9028 |
| language_modeling.md | 14 kB | | c870695f |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 385259f0 |
| masked_language_modeling.md | 13.6 kB | | 9ba34c03 |
| monocular_depth_estimation.html | 29.5 kB | | 9a25af27 |
| monocular_depth_estimation.md | 5.78 kB | | b4ac0466 |
| multiple_choice.html | 51.4 kB | | 42b0709a |
| multiple_choice.md | 9.41 kB | | 779cd926 |
| object_detection.html | 92 kB | | bd6e6d88 |
| object_detection.md | 22.8 kB | | 6f1c2046 |
| prompting.html | 45.6 kB | | ce13d4fd |
| prompting.md | 13.4 kB | | b1246c0c |
| question_answering.html | 54.8 kB | | 133b9909 |
| question_answering.md | 11.3 kB | | f9bf97b6 |
| semantic_segmentation.html | 107 kB | | 1909eae4 |
| semantic_segmentation.md | 21.3 kB | | 2c57ca3c |
| sequence_classification.html | 53.9 kB | | 8ce7dbb8 |
| sequence_classification.md | 10.3 kB | | 330c7aa4 |
| summarization.html | 60.4 kB | | f1ae8370 |
| summarization.md | 17.7 kB | | ab353c19 |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 08656b2f |
| token_classification.md | 13.9 kB | | c9ccaec9 |
| training_vision_backbone.html | 35.9 kB | | 16b6599a |
| training_vision_backbone.md | 8.7 kB | | a5797b8c |
| translation.html | 54.2 kB | | a1542dfc |
| translation.md | 10.4 kB | | d6a48a19 |
| video_classification.html | 89.2 kB | | e41f8fd2 |
| video_classification.md | 20.6 kB | | f0641397 |
| video_text_to_text.html | 25.2 kB | | 9d2178a1 |
| video_text_to_text.md | 6.01 kB | | 0f5617d8 |
| visual_document_retrieval.html | 27 kB | | ce9832f3 |
| visual_document_retrieval.md | 5.68 kB | | 911698db |
| visual_question_answering.html | 69.6 kB | | f55a2cf8 |
| visual_question_answering.md | 14.6 kB | | a9143006 |
| zero_shot_image_classification.html | 29.7 kB | | 69b0c159 |
| zero_shot_image_classification.md | 5.05 kB | | f2345003 |
| zero_shot_object_detection.html | 57.4 kB | | b736dab4 |
| zero_shot_object_detection.md | 10.4 kB | | c7ea1dc0 |