| any_to_any.html | 26.9 kB | | bdc0313d |
| any_to_any.md | 4.85 kB | | d56ece24 |
| asr.html | 71.4 kB | | 1999a548 |
| asr.md | 14.9 kB | | a94d6401 |
| audio_classification.html | 65 kB | | 7ec4256c |
| audio_classification.md | 12.3 kB | | 244157b6 |
| audio_text_to_text.html | 68.7 kB | | ff879891 |
| audio_text_to_text.md | 12.2 kB | | 25f1f3f8 |
| document_question_answering.html | 108 kB | | 95af69ba |
| document_question_answering.md | 24.1 kB | | d4fa1dae |
| image_captioning.html | 49.3 kB | | 06b49703 |
| image_captioning.md | 7.39 kB | | 8f247fba |
| image_classification.html | 60.8 kB | | d9a26ca3 |
| image_classification.md | 10.9 kB | | 379352d2 |
| image_feature_extraction.html | 30.4 kB | | 34e7c061 |
| image_feature_extraction.md | 4.49 kB | | d93a4916 |
| image_text_to_text.html | 60.7 kB | | c98aa7dc |
| image_text_to_text.md | 16.6 kB | | 05926eb3 |
| instance_segmentation.html | 71.2 kB | | 1caee052 |
| instance_segmentation.md | 17.4 kB | | efed2c4e |
| keypoint_detection.html | 25.9 kB | | 4ad4205b |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 23.7 kB | | 5db1c631 |
| keypoint_matching.md | 4.4 kB | | 99cd6c82 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | f82814aa |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 7e97937b |
| language_modeling.html | 62.4 kB | | 09d52b2f |
| language_modeling.md | 14 kB | | bc17b04a |
| mask_generation.html | 79.9 kB | | 47bf489d |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 1fbe97d6 |
| masked_language_modeling.md | 13.6 kB | | 6d76c853 |
| monocular_depth_estimation.html | 29.5 kB | | be93682e |
| monocular_depth_estimation.md | 5.82 kB | | c96d1fcd |
| multiple_choice.html | 51.3 kB | | 45c1bd8a |
| multiple_choice.md | 9.42 kB | | 97c2d32c |
| object_detection.html | 91.9 kB | | 9314789f |
| object_detection.md | 22.8 kB | | f42612de |
| prompting.html | 37 kB | | ee9fb632 |
| prompting.md | 13.4 kB | | 087cd982 |
| question_answering.html | 54.7 kB | | 2a5aaa71 |
| question_answering.md | 11.4 kB | | bf4b37ef |
| semantic_segmentation.html | 114 kB | | 3ba58aa9 |
| semantic_segmentation.md | 23.7 kB | | e15c2d81 |
| sequence_classification.html | 53.7 kB | | dc880cda |
| sequence_classification.md | 10.4 kB | | b69a1742 |
| summarization.html | 60.2 kB | | d874bf93 |
| summarization.md | 17.7 kB | | 937f953c |
| text-to-speech.html | 127 kB | | c75bdb79 |
| text-to-speech.md | 23.6 kB | | 5dcf6538 |
| token_classification.html | 73 kB | | 10338fa0 |
| token_classification.md | 13.9 kB | | 83037bce |
| training_vision_backbone.html | 35.8 kB | | da4eb2a1 |
| training_vision_backbone.md | 8.7 kB | | 172828ef |
| translation.html | 54 kB | | 823beb6c |
| translation.md | 10.4 kB | | 5a6c86bb |
| video_classification.html | 89.4 kB | | 4befd127 |
| video_classification.md | 20.8 kB | | 2159b91d |
| video_text_to_text.html | 25.1 kB | | efc69a68 |
| video_text_to_text.md | 6.01 kB | | 129e0007 |
| visual_document_retrieval.html | 26.9 kB | | ee89b4bd |
| visual_document_retrieval.md | 5.68 kB | | 8f038c0c |
| visual_question_answering.html | 69.7 kB | | 79dc61dc |
| visual_question_answering.md | 14.8 kB | | 6120652e |
| zero_shot_image_classification.html | 29.6 kB | | e04c8130 |
| zero_shot_image_classification.md | 5.05 kB | | ee0b5621 |
| zero_shot_object_detection.html | 57.3 kB | | b0f621a9 |
| zero_shot_object_detection.md | 10.3 kB | | 8050ddea |
