| any_to_any.html | 26.9 kB | | 3b0192bb |
| any_to_any.md | 4.85 kB | | a105684f |
| asr.html | 71.4 kB | | 8c230b48 |
| asr.md | 14.9 kB | | 4dd71c73 |
| audio_classification.html | 65 kB | | e8835e9a |
| audio_classification.md | 12.3 kB | | 95f30e1b |
| audio_text_to_text.html | 69.7 kB | | b0015ac6 |
| audio_text_to_text.md | 12.7 kB | | 3da239cc |
| document_question_answering.html | 108 kB | | 1e8e0c5d |
| document_question_answering.md | 24.1 kB | | 6025cf8b |
| image_captioning.html | 49.3 kB | | 4c29d6c6 |
| image_captioning.md | 7.39 kB | | 0f0785c8 |
| image_classification.html | 60.7 kB | | 2a6461c3 |
| image_classification.md | 10.9 kB | | 9b168bda |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | cae22406 |
| image_text_to_text.md | 16.7 kB | | 608228ac |
| instance_segmentation.html | 74.1 kB | | d4be3fa7 |
| instance_segmentation.md | 18 kB | | 4fe6ea24 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | abcde92c |
| keypoint_matching.md | 4.4 kB | | 551f77dd |
| 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 | | e62ec17a |
| language_modeling.md | 14 kB | | 003add6f |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | c46b6535 |
| masked_language_modeling.md | 13.6 kB | | c0acb0ad |
| monocular_depth_estimation.html | 29.4 kB | | 5d5a8fd1 |
| monocular_depth_estimation.md | 5.78 kB | | 7aab02a5 |
| multiple_choice.html | 51.3 kB | | 2a1f47b2 |
| multiple_choice.md | 9.41 kB | | 6e56676a |
| object_detection.html | 91.9 kB | | af60f94b |
| object_detection.md | 22.8 kB | | ae4cab8a |
| prompting.html | 37.1 kB | | e28399c2 |
| prompting.md | 13.4 kB | | ad3b469d |
| question_answering.html | 54.6 kB | | a0f369b1 |
| question_answering.md | 11.3 kB | | fd7ec9f9 |
| semantic_segmentation.html | 107 kB | | 6bfd133a |
| semantic_segmentation.md | 21.3 kB | | 0a012781 |
| sequence_classification.html | 53.7 kB | | 79fd22e3 |
| sequence_classification.md | 10.3 kB | | d1e4132b |
| summarization.html | 60.2 kB | | c8fd57d4 |
| summarization.md | 17.7 kB | | 068e0381 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | a604968e |
| token_classification.md | 13.9 kB | | e1af8a18 |
| training_vision_backbone.html | 35.8 kB | | a1af5311 |
| training_vision_backbone.md | 8.7 kB | | 2d854adc |
| translation.html | 54 kB | | 203212b6 |
| translation.md | 10.4 kB | | b88d0c9f |
| video_classification.html | 89.3 kB | | 4ecd91df |
| video_classification.md | 20.8 kB | | 6874cb63 |
| video_text_to_text.html | 25.1 kB | | e8180fea |
| video_text_to_text.md | 6.01 kB | | 07dc037e |
| visual_document_retrieval.html | 26.9 kB | | cdfb7297 |
| visual_document_retrieval.md | 5.68 kB | | e7a4a3a2 |
| visual_question_answering.html | 69.7 kB | | 8b830a4f |
| visual_question_answering.md | 14.8 kB | | f80cb800 |
| zero_shot_image_classification.html | 29.6 kB | | 592765ed |
| zero_shot_image_classification.md | 5.05 kB | | dd6be29b |
| zero_shot_object_detection.html | 57.3 kB | | 81afa924 |
| zero_shot_object_detection.md | 10.4 kB | | 4e021818 |