| any_to_any.html | 27.7 kB | | 1b6cd9e2 |
| any_to_any.md | 4.85 kB | | d5382fe4 |
| asr.html | 72.8 kB | | 5bde87c0 |
| asr.md | 14.9 kB | | f8b9f20b |
| audio_classification.html | 66.5 kB | | fca4b792 |
| audio_classification.md | 12.3 kB | | 06105bbc |
| audio_text_to_text.html | 69.9 kB | | 91e2d39c |
| audio_text_to_text.md | 12.2 kB | | d2aa0458 |
| document_question_answering.html | 110 kB | | 8a19a07d |
| document_question_answering.md | 24.1 kB | | 3fd73efe |
| idefics.html | 69.5 kB | | b5fc0e32 |
| idefics.md | 18.9 kB | | d78fd794 |
| image_captioning.html | 50.6 kB | | a20e82a7 |
| image_captioning.md | 7.4 kB | | 631073e5 |
| image_classification.html | 62.2 kB | | 202c0832 |
| image_classification.md | 10.9 kB | | 78cb2826 |
| image_feature_extraction.html | 31.2 kB | | 85403e20 |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 62.1 kB | | 2c5f2761 |
| image_text_to_text.md | 16.6 kB | | 9b5fbc9f |
| instance_segmentation.html | 72.6 kB | | 1f6565ef |
| instance_segmentation.md | 17.4 kB | | a0210c11 |
| keypoint_detection.html | 26.6 kB | | 73251e4b |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | 3b078544 |
| keypoint_matching.md | 4.4 kB | | ecb64f05 |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | c7c2c4a4 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.8 kB | | d64f0893 |
| language_modeling.md | 14 kB | | d189ba31 |
| mask_generation.html | 81.5 kB | | 7ed8bd99 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.7 kB | | ba5f9021 |
| masked_language_modeling.md | 13.6 kB | | 3ec755dd |
| monocular_depth_estimation.html | 30.6 kB | | 7913f26a |
| monocular_depth_estimation.md | 5.82 kB | | 292968e7 |
| multiple_choice.html | 52.4 kB | | 449cf64e |
| multiple_choice.md | 9.42 kB | | 9c1f17eb |
| object_detection.html | 93.5 kB | | 52df0659 |
| object_detection.md | 22.8 kB | | 6a83be71 |
| prompting.html | 37.8 kB | | 76513483 |
| prompting.md | 13.4 kB | | 6d01a872 |
| question_answering.html | 56 kB | | 155625fe |
| question_answering.md | 11.4 kB | | e2da751b |
| semantic_segmentation.html | 116 kB | | dd4d9241 |
| semantic_segmentation.md | 23.7 kB | | c1ea2c13 |
| sequence_classification.html | 55 kB | | 0ce3ba17 |
| sequence_classification.md | 10.3 kB | | c92be2fe |
| summarization.html | 61.5 kB | | 5b65eb5c |
| summarization.md | 17.7 kB | | d377ec86 |
| text-to-speech.html | 130 kB | | 066deaf1 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.4 kB | | e9ced662 |
| token_classification.md | 13.9 kB | | 1b66702b |
| training_vision_backbone.html | 36.8 kB | | 58562a44 |
| training_vision_backbone.md | 8.7 kB | | c4cb8874 |
| translation.html | 55.2 kB | | a3503e37 |
| translation.md | 10.4 kB | | 26587f50 |
| video_classification.html | 91.4 kB | | 9883afe8 |
| video_classification.md | 20.8 kB | | e1638d26 |
| video_text_to_text.html | 26 kB | | e6987fbe |
| video_text_to_text.md | 5.91 kB | | 4c68684e |
| visual_document_retrieval.html | 27.9 kB | | 2b791cb4 |
| visual_document_retrieval.md | 5.68 kB | | 409183c0 |
| visual_question_answering.html | 71.5 kB | | 6c255363 |
| visual_question_answering.md | 14.8 kB | | d6af7f4d |
| zero_shot_image_classification.html | 30.5 kB | | 11311934 |
| zero_shot_image_classification.md | 5.05 kB | | 0dc7f222 |
| zero_shot_object_detection.html | 58.6 kB | | d14d5cf6 |
| zero_shot_object_detection.md | 10.3 kB | | c4acd255 |
