| any_to_any.html | 26.9 kB | | 213366be |
| any_to_any.md | 4.85 kB | | 178bfcb4 |
| asr.html | 71.4 kB | | ba377af8 |
| asr.md | 14.9 kB | | 7abb3065 |
| audio_classification.html | 65 kB | | b46abf3b |
| audio_classification.md | 12.3 kB | | 8e6e105f |
| audio_text_to_text.html | 69.7 kB | | 723c9eca |
| audio_text_to_text.md | 12.7 kB | | 86603235 |
| document_question_answering.html | 108 kB | | 2b2cdcb6 |
| document_question_answering.md | 24.1 kB | | e1463228 |
| image_captioning.html | 49.3 kB | | c8ce67a7 |
| image_captioning.md | 7.39 kB | | e51921f6 |
| image_classification.html | 60.7 kB | | 6c2aa068 |
| image_classification.md | 10.9 kB | | a4c07335 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | c84646e3 |
| image_text_to_text.md | 16.7 kB | | 894260f5 |
| instance_segmentation.html | 74.1 kB | | 5bbf3c06 |
| instance_segmentation.md | 18 kB | | 3df2c66f |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 7139784a |
| keypoint_matching.md | 4.4 kB | | 05c20478 |
| 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 | | 2bda74a7 |
| language_modeling.md | 14 kB | | aa13cddb |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 80ca14dd |
| masked_language_modeling.md | 13.6 kB | | 81465a16 |
| monocular_depth_estimation.html | 29.4 kB | | f944fb6d |
| monocular_depth_estimation.md | 5.78 kB | | 593d19b4 |
| multiple_choice.html | 51.3 kB | | 008a24fb |
| multiple_choice.md | 9.41 kB | | a2ac6320 |
| object_detection.html | 91.9 kB | | 7d81c7ba |
| object_detection.md | 22.8 kB | | 9491337c |
| prompting.html | 37.1 kB | | a3640422 |
| prompting.md | 13.4 kB | | 4b9d22f3 |
| question_answering.html | 54.6 kB | | e8afd10b |
| question_answering.md | 11.3 kB | | 20422bd5 |
| semantic_segmentation.html | 107 kB | | 9ab0ee7a |
| semantic_segmentation.md | 21.3 kB | | 3e1fe3c0 |
| sequence_classification.html | 53.8 kB | | 32ef083c |
| sequence_classification.md | 10.3 kB | | 2bb02079 |
| summarization.html | 60.2 kB | | 4314beff |
| summarization.md | 17.7 kB | | 43554628 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | cf3e9d5b |
| token_classification.md | 13.9 kB | | df1ae77f |
| training_vision_backbone.html | 35.8 kB | | 27ff0978 |
| training_vision_backbone.md | 8.7 kB | | dbfa85e4 |
| translation.html | 54 kB | | 9842540e |
| translation.md | 10.4 kB | | 3e278fc4 |
| video_classification.html | 89.3 kB | | 28a0f3e4 |
| video_classification.md | 20.8 kB | | 247a4158 |
| video_text_to_text.html | 25.1 kB | | e5b32fab |
| video_text_to_text.md | 6.01 kB | | b21050a1 |
| visual_document_retrieval.html | 26.9 kB | | b1bba8e2 |
| visual_document_retrieval.md | 5.68 kB | | b93b4ddb |
| visual_question_answering.html | 69.7 kB | | 20e547cf |
| visual_question_answering.md | 14.8 kB | | 2ad00e39 |
| zero_shot_image_classification.html | 29.6 kB | | 798ef2cb |
| zero_shot_image_classification.md | 5.05 kB | | c9106095 |
| zero_shot_object_detection.html | 57.3 kB | | 8de5327b |
| zero_shot_object_detection.md | 10.4 kB | | 9c1478fa |