| any_to_any.html | 26.9 kB | | 875e4696 |
| any_to_any.md | 4.85 kB | | d30e98f8 |
| asr.html | 71.4 kB | | c119cae8 |
| asr.md | 14.9 kB | | f250f5b5 |
| audio_classification.html | 65 kB | | 03e901b8 |
| audio_classification.md | 12.3 kB | | e53d1c98 |
| audio_text_to_text.html | 69.7 kB | | 88ee445c |
| audio_text_to_text.md | 12.7 kB | | 3bb0958f |
| document_question_answering.html | 108 kB | | d803971f |
| document_question_answering.md | 24.1 kB | | d334e612 |
| image_captioning.html | 49.3 kB | | 8cf65ad4 |
| image_captioning.md | 7.39 kB | | 432c58d4 |
| image_classification.html | 60.7 kB | | cf6b3662 |
| image_classification.md | 10.9 kB | | cb59009b |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 3f45b8ef |
| image_text_to_text.md | 16.7 kB | | c8be51ac |
| instance_segmentation.html | 74.1 kB | | 1e404d2d |
| instance_segmentation.md | 18 kB | | bbdd92e3 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 5d4c360e |
| keypoint_matching.md | 4.4 kB | | 70438752 |
| 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 | | 29efa82d |
| language_modeling.md | 14 kB | | c3e6cf90 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 46b4750e |
| masked_language_modeling.md | 13.6 kB | | 3f440012 |
| monocular_depth_estimation.html | 29.4 kB | | 6cba7f37 |
| monocular_depth_estimation.md | 5.78 kB | | 056d55af |
| multiple_choice.html | 51.3 kB | | 5bfd710e |
| multiple_choice.md | 9.41 kB | | 84f7405a |
| object_detection.html | 91.9 kB | | 666aa14c |
| object_detection.md | 22.8 kB | | 7edcd6cd |
| prompting.html | 37.1 kB | | ce2e8bfa |
| prompting.md | 13.4 kB | | 93399ccd |
| question_answering.html | 54.6 kB | | 7549a46e |
| question_answering.md | 11.3 kB | | 9405bbc4 |
| semantic_segmentation.html | 107 kB | | 553988b1 |
| semantic_segmentation.md | 21.3 kB | | 9159dcbe |
| sequence_classification.html | 53.7 kB | | 0e0ee21c |
| sequence_classification.md | 10.3 kB | | c473ff03 |
| summarization.html | 60.2 kB | | a1a6b76b |
| summarization.md | 17.7 kB | | 917263d7 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | cb0deb44 |
| token_classification.md | 13.9 kB | | 151329f4 |
| training_vision_backbone.html | 35.8 kB | | 3c5e657e |
| training_vision_backbone.md | 8.7 kB | | f889b31a |
| translation.html | 54 kB | | c62f39f6 |
| translation.md | 10.4 kB | | dfffa20e |
| video_classification.html | 89.3 kB | | bf927b29 |
| video_classification.md | 20.8 kB | | 0ff05482 |
| video_text_to_text.html | 25.1 kB | | 1ca4b331 |
| video_text_to_text.md | 6.01 kB | | 0a92dc75 |
| visual_document_retrieval.html | 26.9 kB | | 9826a374 |
| visual_document_retrieval.md | 5.68 kB | | ae11b193 |
| visual_question_answering.html | 69.7 kB | | e3bb3326 |
| visual_question_answering.md | 14.8 kB | | 0b242710 |
| zero_shot_image_classification.html | 29.6 kB | | 7d3c32e8 |
| zero_shot_image_classification.md | 5.05 kB | | 30442ca3 |
| zero_shot_object_detection.html | 57.3 kB | | 73c81132 |
| zero_shot_object_detection.md | 10.4 kB | | 30cbbc28 |