| any_to_any.html | 26.9 kB | | 89c0138e |
| any_to_any.md | 4.85 kB | | ab5604a8 |
| asr.html | 71.4 kB | | 5e86126f |
| asr.md | 14.9 kB | | 8d27a4ea |
| audio_classification.html | 65 kB | | 289c3cc9 |
| audio_classification.md | 12.3 kB | | 84c5740c |
| audio_text_to_text.html | 68.7 kB | | cf08f578 |
| audio_text_to_text.md | 12.2 kB | | 1dd76f79 |
| document_question_answering.html | 108 kB | | fb722b98 |
| document_question_answering.md | 24.1 kB | | f9e83386 |
| idefics.html | 67.9 kB | | 8d90260d |
| idefics.md | 18.9 kB | | bd123d57 |
| image_captioning.html | 49.3 kB | | 960fff3a |
| image_captioning.md | 7.39 kB | | bef79e7e |
| image_classification.html | 60.8 kB | | 6aa08dae |
| image_classification.md | 10.9 kB | | b739eeb1 |
| image_feature_extraction.html | 30.4 kB | | efcdebab |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 60.7 kB | | fb2299e1 |
| image_text_to_text.md | 16.6 kB | | 6247ba00 |
| instance_segmentation.html | 71.1 kB | | e2991f02 |
| instance_segmentation.md | 17.4 kB | | e4ddc66e |
| keypoint_detection.html | 25.9 kB | | 83e71e59 |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 23.7 kB | | 9b1433ee |
| keypoint_matching.md | 4.4 kB | | 9b5655c2 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 1b583df9 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 62.4 kB | | 88baf462 |
| language_modeling.md | 14 kB | | 890d1d7a |
| mask_generation.html | 79.8 kB | | c88133c5 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 63.3 kB | | 9a0b13c4 |
| masked_language_modeling.md | 13.6 kB | | fe2a9072 |
| monocular_depth_estimation.html | 29.5 kB | | 2f382daa |
| monocular_depth_estimation.md | 5.82 kB | | cb25014d |
| multiple_choice.html | 51.3 kB | | 5731c4cf |
| multiple_choice.md | 9.42 kB | | 5b340e40 |
| object_detection.html | 91.9 kB | | c90676a1 |
| object_detection.md | 22.8 kB | | 898d5b6e |
| prompting.html | 37 kB | | 9d1a79d9 |
| prompting.md | 13.4 kB | | c1250f9b |
| question_answering.html | 54.7 kB | | 6185557c |
| question_answering.md | 11.4 kB | | d5648fbf |
| semantic_segmentation.html | 114 kB | | e53043dd |
| semantic_segmentation.md | 23.7 kB | | a7cc6143 |
| sequence_classification.html | 53.7 kB | | a9797438 |
| sequence_classification.md | 10.4 kB | | fad8b0e4 |
| summarization.html | 60.2 kB | | 94b3e3a7 |
| summarization.md | 17.7 kB | | 6bc614ae |
| text-to-speech.html | 127 kB | | 62c38a21 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 73 kB | | 82033244 |
| token_classification.md | 13.9 kB | | 4b671800 |
| training_vision_backbone.html | 35.8 kB | | 4dd51e01 |
| training_vision_backbone.md | 8.7 kB | | e16b60e0 |
| translation.html | 54 kB | | 5c906ff7 |
| translation.md | 10.4 kB | | 4ed38609 |
| video_classification.html | 89.4 kB | | 56fe1f54 |
| video_classification.md | 20.8 kB | | 6000bca1 |
| video_text_to_text.html | 24.9 kB | | 92b58174 |
| video_text_to_text.md | 5.91 kB | | 1c7d74d9 |
| visual_document_retrieval.html | 26.9 kB | | 8eae3d35 |
| visual_document_retrieval.md | 5.68 kB | | 1afcb878 |
| visual_question_answering.html | 69.7 kB | | d4658ba2 |
| visual_question_answering.md | 14.8 kB | | 8f42872a |
| zero_shot_image_classification.html | 29.6 kB | | cbefbc00 |
| zero_shot_image_classification.md | 5.05 kB | | 317c21b2 |
| zero_shot_object_detection.html | 57.3 kB | | c436d933 |
| zero_shot_object_detection.md | 10.3 kB | | f5b4b38b |
