| any_to_any.html | 27 kB | | 2ec56022 |
| any_to_any.md | 4.85 kB | | e29c9c34 |
| asr.html | 71.5 kB | | 5b3a0f46 |
| asr.md | 14.9 kB | | a3e402f9 |
| audio_classification.html | 65.1 kB | | 3c38640c |
| audio_classification.md | 12.3 kB | | 15105f9f |
| audio_text_to_text.html | 69.9 kB | | 2126d9e2 |
| audio_text_to_text.md | 12.7 kB | | c7b7f353 |
| document_question_answering.html | 108 kB | | eae50330 |
| document_question_answering.md | 24.1 kB | | fe5f5469 |
| image_captioning.html | 49.5 kB | | 4c6619fb |
| image_captioning.md | 7.39 kB | | cf50930c |
| image_classification.html | 60.9 kB | | dfe9a8a6 |
| image_classification.md | 10.9 kB | | a21251ba |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | b3bf5d8f |
| image_text_to_text.md | 17.1 kB | | aea94a29 |
| instance_segmentation.html | 74.3 kB | | c3049612 |
| instance_segmentation.md | 18 kB | | 70e8a95f |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 893e93fa |
| keypoint_matching.md | 4.4 kB | | 8125f52c |
| 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 | | 46f810cc |
| language_modeling.md | 14 kB | | 995083cf |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 22432d14 |
| masked_language_modeling.md | 13.6 kB | | 3756f566 |
| monocular_depth_estimation.html | 29.5 kB | | 158abefb |
| monocular_depth_estimation.md | 5.78 kB | | 164db7a9 |
| multiple_choice.html | 51.4 kB | | 52bd029b |
| multiple_choice.md | 9.41 kB | | cc2bdb77 |
| object_detection.html | 92 kB | | 6187ae1a |
| object_detection.md | 22.8 kB | | 6d866a25 |
| prompting.html | 45.6 kB | | 299ceba8 |
| prompting.md | 13.4 kB | | db1d67f5 |
| question_answering.html | 54.8 kB | | cedbf72a |
| question_answering.md | 11.3 kB | | 6ec65a54 |
| semantic_segmentation.html | 107 kB | | 65e02702 |
| semantic_segmentation.md | 21.3 kB | | fd4b6d2c |
| sequence_classification.html | 53.9 kB | | 15d33af5 |
| sequence_classification.md | 10.3 kB | | a426dae3 |
| summarization.html | 60.4 kB | | 00035469 |
| summarization.md | 17.7 kB | | 4a3eb61b |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 3f64be5f |
| token_classification.md | 13.9 kB | | 7474c7bf |
| training_vision_backbone.html | 35.9 kB | | bddd76df |
| training_vision_backbone.md | 8.7 kB | | 339993f1 |
| translation.html | 54.2 kB | | 858ccaaa |
| translation.md | 10.4 kB | | fa2f694f |
| video_classification.html | 89.5 kB | | d535ce50 |
| video_classification.md | 20.8 kB | | 826872cb |
| video_text_to_text.html | 25.2 kB | | 4dcafb1f |
| video_text_to_text.md | 6.01 kB | | 83282c8d |
| visual_document_retrieval.html | 27 kB | | 1daa27e2 |
| visual_document_retrieval.md | 5.68 kB | | cd9e563e |
| visual_question_answering.html | 69.9 kB | | e978d164 |
| visual_question_answering.md | 14.8 kB | | f190e09c |
| zero_shot_image_classification.html | 29.7 kB | | b5949a9a |
| zero_shot_image_classification.md | 5.05 kB | | 1adadef0 |
| zero_shot_object_detection.html | 57.4 kB | | acca6172 |
| zero_shot_object_detection.md | 10.4 kB | | c3b74807 |