| any_to_any.html | 26.9 kB | | 287ca4c5 |
| any_to_any.md | 4.85 kB | | 3aff36ad |
| asr.html | 71.4 kB | | 9c50a543 |
| asr.md | 14.9 kB | | 31f39782 |
| audio_classification.html | 65 kB | | 5d01c333 |
| audio_classification.md | 12.3 kB | | 26ff6bd8 |
| audio_text_to_text.html | 69.7 kB | | b1ed17a3 |
| audio_text_to_text.md | 12.7 kB | | 491e06fc |
| document_question_answering.html | 108 kB | | 84c587ab |
| document_question_answering.md | 24.1 kB | | 63a0b44f |
| image_captioning.html | 49.3 kB | | ec50c2bb |
| image_captioning.md | 7.39 kB | | c2e2fbf5 |
| image_classification.html | 60.7 kB | | 6688daf6 |
| image_classification.md | 10.9 kB | | 964b99bd |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | f1bfb117 |
| image_text_to_text.md | 17.1 kB | | d987665e |
| instance_segmentation.html | 74.1 kB | | c4b09052 |
| instance_segmentation.md | 18 kB | | a2481699 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 3567d4ec |
| keypoint_matching.md | 4.4 kB | | 38464e59 |
| 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 | | ee75c0e1 |
| language_modeling.md | 14 kB | | 5d874cea |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | d2aec8be |
| masked_language_modeling.md | 13.6 kB | | b9278050 |
| monocular_depth_estimation.html | 29.4 kB | | a74f9d86 |
| monocular_depth_estimation.md | 5.78 kB | | 700c6805 |
| multiple_choice.html | 51.3 kB | | d715f813 |
| multiple_choice.md | 9.41 kB | | 16dda0dc |
| object_detection.html | 91.9 kB | | 369b3ce1 |
| object_detection.md | 22.8 kB | | 8e5dc3b0 |
| prompting.html | 37.1 kB | | 0b9653af |
| prompting.md | 13.4 kB | | 2355f1a5 |
| question_answering.html | 54.6 kB | | 2adbc7c7 |
| question_answering.md | 11.3 kB | | 1d81a161 |
| semantic_segmentation.html | 107 kB | | 260bb867 |
| semantic_segmentation.md | 21.3 kB | | 40e4d431 |
| sequence_classification.html | 53.8 kB | | 6f92d1dd |
| sequence_classification.md | 10.3 kB | | f30f7956 |
| summarization.html | 60.2 kB | | 20f8a9a2 |
| summarization.md | 17.7 kB | | f79f7b4a |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 27d02323 |
| token_classification.md | 13.9 kB | | c35117d1 |
| training_vision_backbone.html | 35.8 kB | | 270e6994 |
| training_vision_backbone.md | 8.7 kB | | c27e3b8a |
| translation.html | 54 kB | | e746e9dd |
| translation.md | 10.4 kB | | d0e700d9 |
| video_classification.html | 89.3 kB | | e31ffac8 |
| video_classification.md | 20.8 kB | | d6998e73 |
| video_text_to_text.html | 25.1 kB | | f2611b75 |
| video_text_to_text.md | 6.01 kB | | 79b07cdb |
| visual_document_retrieval.html | 26.9 kB | | 61c8bb56 |
| visual_document_retrieval.md | 5.68 kB | | 4c5e8f2a |
| visual_question_answering.html | 69.7 kB | | d8931eac |
| visual_question_answering.md | 14.8 kB | | 2c94af7d |
| zero_shot_image_classification.html | 29.6 kB | | b69f88a3 |
| zero_shot_image_classification.md | 5.05 kB | | 3b52b453 |
| zero_shot_object_detection.html | 57.3 kB | | fc037589 |
| zero_shot_object_detection.md | 10.4 kB | | 0d64fcff |