| any_to_any.html | 27.7 kB | | ed404688 |
| any_to_any.md | 4.85 kB | | 3c79de77 |
| asr.html | 72.8 kB | | 349069cf |
| asr.md | 14.9 kB | | d8256ced |
| audio_classification.html | 66.5 kB | | 69573970 |
| audio_classification.md | 12.3 kB | | 92822b2a |
| audio_text_to_text.html | 69.9 kB | | 5e4e565a |
| audio_text_to_text.md | 12.2 kB | | 128719d7 |
| document_question_answering.html | 110 kB | | 5d052f54 |
| document_question_answering.md | 24.1 kB | | 5ee82ae6 |
| idefics.html | 69.5 kB | | 344cab4b |
| idefics.md | 18.9 kB | | 910e889b |
| image_captioning.html | 50.6 kB | | 73cf0bb7 |
| image_captioning.md | 7.4 kB | | 936fdd52 |
| image_classification.html | 62.2 kB | | 3c1749d0 |
| image_classification.md | 10.9 kB | | da89958f |
| image_feature_extraction.html | 31.2 kB | | c5909cea |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 62.1 kB | | 6da575ba |
| image_text_to_text.md | 16.6 kB | | 0edef757 |
| instance_segmentation.html | 72.6 kB | | c2dc96be |
| instance_segmentation.md | 17.4 kB | | 014f9875 |
| keypoint_detection.html | 26.6 kB | | 4bc6cbba |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | 80d14f06 |
| keypoint_matching.md | 4.4 kB | | c94b8652 |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | 33da7fe7 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.8 kB | | 4827c508 |
| language_modeling.md | 14 kB | | 9f425c59 |
| mask_generation.html | 81.5 kB | | 81d5db59 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.7 kB | | 9cb0c46a |
| masked_language_modeling.md | 13.6 kB | | 71a898ae |
| monocular_depth_estimation.html | 30.6 kB | | ee50c741 |
| monocular_depth_estimation.md | 5.82 kB | | 243112b9 |
| multiple_choice.html | 52.4 kB | | 12068ae8 |
| multiple_choice.md | 9.42 kB | | 328aa32b |
| object_detection.html | 93.5 kB | | 9651ded6 |
| object_detection.md | 22.8 kB | | 4cc8740d |
| prompting.html | 37.8 kB | | fe0dcb29 |
| prompting.md | 13.4 kB | | dc9a1a25 |
| question_answering.html | 56 kB | | 3481e874 |
| question_answering.md | 11.4 kB | | 5c24a584 |
| semantic_segmentation.html | 116 kB | | 60e5316c |
| semantic_segmentation.md | 23.7 kB | | 016b67cd |
| sequence_classification.html | 55 kB | | e4c95e73 |
| sequence_classification.md | 10.3 kB | | bcb9da4f |
| summarization.html | 61.5 kB | | be80919c |
| summarization.md | 17.7 kB | | 789e4549 |
| text-to-speech.html | 130 kB | | 856f7277 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.4 kB | | 8781fd7b |
| token_classification.md | 13.9 kB | | bb6338fd |
| training_vision_backbone.html | 36.8 kB | | a2d40743 |
| training_vision_backbone.md | 8.7 kB | | 1c10c3d1 |
| translation.html | 55.2 kB | | e98fb9cb |
| translation.md | 10.4 kB | | a63940fb |
| video_classification.html | 91.4 kB | | f34d3155 |
| video_classification.md | 20.8 kB | | 77423b1b |
| video_text_to_text.html | 26 kB | | ece7b333 |
| video_text_to_text.md | 5.91 kB | | f4b5b84e |
| visual_document_retrieval.html | 27.9 kB | | 3673540b |
| visual_document_retrieval.md | 5.68 kB | | 234a676d |
| visual_question_answering.html | 71.5 kB | | fa624704 |
| visual_question_answering.md | 14.8 kB | | bfe5ff88 |
| zero_shot_image_classification.html | 30.5 kB | | e0098ed7 |
| zero_shot_image_classification.md | 5.05 kB | | 651defea |
| zero_shot_object_detection.html | 58.6 kB | | 90d3ba51 |
| zero_shot_object_detection.md | 10.3 kB | | 28cb907c |
