| asr.html | 72.3 kB | | a80bd9e7 |
| asr.md | 14.8 kB | | 19bfa833 |
| audio_classification.html | 66.1 kB | | e14d6a68 |
| audio_classification.md | 12.2 kB | | 24b8ce3b |
| document_question_answering.html | 109 kB | | 9933c824 |
| document_question_answering.md | 23.4 kB | | 8d146285 |
| idefics.html | 69.4 kB | | 376cd6cd |
| idefics.md | 18.5 kB | | bd743c02 |
| image_captioning.html | 50.3 kB | | 381bf99c |
| image_captioning.md | 7.4 kB | | 4a286fec |
| image_classification.html | 61.7 kB | | 27d7cc18 |
| image_classification.md | 10.8 kB | | 01258e47 |
| image_feature_extraction.html | 31 kB | | 4302a58c |
| image_feature_extraction.md | 4.48 kB | | d1f18593 |
| image_text_to_text.html | 48.2 kB | | 4f77143f |
| image_text_to_text.md | 10.6 kB | | 57c6ff40 |
| image_to_image.html | 28.5 kB | | d6d2ea54 |
| image_to_image.md | 4.11 kB | | b3229c58 |
| keypoint_detection.html | 26.6 kB | | 78cf69e9 |
| keypoint_detection.md | 4.4 kB | | b8776f93 |
| keypoint_matching.html | 24.4 kB | | 0e4cf027 |
| keypoint_matching.md | 4.03 kB | | 64616d4f |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 8178323b |
| knowledge_distillation_for_image_classification.md | 7.75 kB | | db559091 |
| language_modeling.html | 63.6 kB | | d194933f |
| language_modeling.md | 14 kB | | a865f480 |
| mask_generation.html | 39.5 kB | | 5ac54a8b |
| mask_generation.md | 6.93 kB | | af0e20ca |
| masked_language_modeling.html | 64.4 kB | | 983c2edd |
| masked_language_modeling.md | 13.6 kB | | e22a7b28 |
| monocular_depth_estimation.html | 30.5 kB | | 9ded8c21 |
| monocular_depth_estimation.md | 5.82 kB | | 98ab8e96 |
| multiple_choice.html | 52.3 kB | | 4d306942 |
| multiple_choice.md | 9.42 kB | | d60cb1b1 |
| object_detection.html | 122 kB | | dd913374 |
| object_detection.md | 40.8 kB | | 6c8ab730 |
| prompting.html | 37.6 kB | | 3a9ed022 |
| prompting.md | 13.2 kB | | ebc0248e |
| question_answering.html | 58.5 kB | | 3db04897 |
| question_answering.md | 11.7 kB | | aa021f21 |
| semantic_segmentation.html | 116 kB | | 07a178ed |
| semantic_segmentation.md | 22.4 kB | | c71cd287 |
| sequence_classification.html | 54.8 kB | | 4f976ea0 |
| sequence_classification.md | 10.3 kB | | 2d57d62f |
| summarization.html | 63.8 kB | | 2bc60eef |
| summarization.md | 18.5 kB | | 7c6f886d |
| text-to-speech.html | 123 kB | | 707e173c |
| text-to-speech.md | 22.3 kB | | 841b0176 |
| token_classification.html | 74.2 kB | | 6d5d0b92 |
| token_classification.md | 13.9 kB | | dd884d28 |
| training_vision_backbone.html | 36.6 kB | | fc9b76f0 |
| training_vision_backbone.md | 8.52 kB | | 0f95ea28 |
| translation.html | 57.8 kB | | e1fab417 |
| translation.md | 11.3 kB | | 18ace529 |
| video_classification.html | 91 kB | | 9bc3382f |
| video_classification.md | 20.8 kB | | 3fd515a0 |
| video_text_to_text.html | 23.3 kB | | f32b7ea6 |
| video_text_to_text.md | 5.12 kB | | d2fe14e8 |
| visual_document_retrieval.html | 27.7 kB | | eee6491a |
| visual_document_retrieval.md | 5.12 kB | | 01ca3455 |
| visual_question_answering.html | 75.6 kB | | 50c13756 |
| visual_question_answering.md | 15.6 kB | | e161de30 |
| zero_shot_image_classification.html | 30.4 kB | | 9626b6bc |
| zero_shot_image_classification.md | 5.05 kB | | 4f7aea6e |
| zero_shot_object_detection.html | 58.4 kB | | 7c484326 |
| zero_shot_object_detection.md | 10.3 kB | | ab5d3be4 |
