| any_to_any.html | 27 kB | | 1f0f1ab5 |
| any_to_any.md | 4.85 kB | | c6a3e84f |
| asr.html | 71.5 kB | | af1c89b3 |
| asr.md | 14.9 kB | | 5e515be0 |
| audio_classification.html | 65.2 kB | | 655d8c12 |
| audio_classification.md | 12.3 kB | | 1a6ef8e2 |
| audio_text_to_text.html | 69.9 kB | | 3de6b0db |
| audio_text_to_text.md | 12.7 kB | | 819bdabb |
| document_question_answering.html | 108 kB | | 9790f7b3 |
| document_question_answering.md | 24.1 kB | | 3ecc35a0 |
| image_captioning.html | 49.5 kB | | 79e5f437 |
| image_captioning.md | 7.39 kB | | bc555f74 |
| image_classification.html | 60.9 kB | | 68a869fd |
| image_classification.md | 10.9 kB | | eaa5303a |
| image_feature_extraction.html | 30.5 kB | | eede085f |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | 00555022 |
| image_text_to_text.md | 17.1 kB | | c81295f9 |
| instance_segmentation.html | 74.3 kB | | 7bceb51b |
| instance_segmentation.md | 18 kB | | 8404698b |
| keypoint_detection.html | 26 kB | | bfa5115d |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 2d4a7baf |
| keypoint_matching.md | 4.4 kB | | 734b532d |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | d3943efb |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | c2e9edc0 |
| language_modeling.md | 14 kB | | 42766ebe |
| mask_generation.html | 80 kB | | 4fbc2918 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 8a956712 |
| masked_language_modeling.md | 13.6 kB | | 542f0e52 |
| monocular_depth_estimation.html | 29.5 kB | | 524135df |
| monocular_depth_estimation.md | 5.78 kB | | 715dc071 |
| multiple_choice.html | 51.4 kB | | 45d1a608 |
| multiple_choice.md | 9.41 kB | | c1802fc2 |
| object_detection.html | 92 kB | | 99b7d547 |
| object_detection.md | 22.8 kB | | fad1e18d |
| prompting.html | 45.6 kB | | 23350c38 |
| prompting.md | 13.4 kB | | f813cd67 |
| question_answering.html | 54.8 kB | | 5d1dbee1 |
| question_answering.md | 11.3 kB | | cd9d17ec |
| semantic_segmentation.html | 107 kB | | 105e7c27 |
| semantic_segmentation.md | 21.3 kB | | e16e7852 |
| sequence_classification.html | 53.9 kB | | 028bfe8d |
| sequence_classification.md | 10.3 kB | | 33bf74c8 |
| summarization.html | 60.4 kB | | f3f6a346 |
| summarization.md | 17.7 kB | | a0ef4bef |
| text-to-speech.html | 127 kB | | 06bf12d6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 8a576007 |
| token_classification.md | 13.9 kB | | 10116e43 |
| training_vision_backbone.html | 35.9 kB | | e1349a12 |
| training_vision_backbone.md | 8.7 kB | | ecc7bbfa |
| translation.html | 54.2 kB | | a172b398 |
| translation.md | 10.4 kB | | ab9a47ec |
| video_classification.html | 89.5 kB | | fe11b07a |
| video_classification.md | 20.8 kB | | fd35d01c |
| video_text_to_text.html | 25.2 kB | | 475c14b7 |
| video_text_to_text.md | 6.01 kB | | 76f63ffc |
| visual_document_retrieval.html | 27 kB | | aada5731 |
| visual_document_retrieval.md | 5.68 kB | | 5c7a798a |
| visual_question_answering.html | 69.9 kB | | 9b387573 |
| visual_question_answering.md | 14.8 kB | | eab181d2 |
| zero_shot_image_classification.html | 29.7 kB | | 1287ca71 |
| zero_shot_image_classification.md | 5.05 kB | | 51fd8ab0 |
| zero_shot_object_detection.html | 57.4 kB | | ca5eeafe |
| zero_shot_object_detection.md | 10.4 kB | | ea6c8fdb |