| any_to_any.html | 27 kB | | cb94a59c |
| any_to_any.md | 4.85 kB | | 6fc12aa7 |
| asr.html | 71.5 kB | | a5906fc9 |
| asr.md | 14.9 kB | | 9cb1e735 |
| audio_classification.html | 65.2 kB | | 11b38552 |
| audio_classification.md | 12.3 kB | | 8ae33d11 |
| audio_text_to_text.html | 69.9 kB | | ec4a0299 |
| audio_text_to_text.md | 12.7 kB | | 77e0d7b6 |
| document_question_answering.html | 108 kB | | 938c61e4 |
| document_question_answering.md | 24.1 kB | | 1781f68f |
| image_captioning.html | 49.5 kB | | c88c7aef |
| image_captioning.md | 7.39 kB | | 7c0359ad |
| image_classification.html | 60.9 kB | | 3a15b112 |
| image_classification.md | 10.9 kB | | c65c194c |
| image_feature_extraction.html | 30.5 kB | | 35f6dc51 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | 2f9d018f |
| image_text_to_text.md | 17.1 kB | | 880719d0 |
| instance_segmentation.html | 74.3 kB | | 7eff9250 |
| instance_segmentation.md | 18 kB | | b8a7ca4a |
| keypoint_detection.html | 26 kB | | b27ebc03 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | b25d490d |
| keypoint_matching.md | 4.4 kB | | 794c57ec |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 2d6feaf2 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | a101ba03 |
| language_modeling.md | 14 kB | | 449fa6e3 |
| mask_generation.html | 80 kB | | 3403429a |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 56ae9380 |
| masked_language_modeling.md | 13.6 kB | | 7e949106 |
| monocular_depth_estimation.html | 29.5 kB | | 6433ebd1 |
| monocular_depth_estimation.md | 5.78 kB | | 2db28b1b |
| multiple_choice.html | 51.4 kB | | 86a36b39 |
| multiple_choice.md | 9.41 kB | | b4f79faf |
| object_detection.html | 92 kB | | 7e7a2d0e |
| object_detection.md | 22.8 kB | | f9a58159 |
| prompting.html | 45.6 kB | | 386dcafa |
| prompting.md | 13.4 kB | | c8cfb265 |
| question_answering.html | 54.8 kB | | 76b5d8b4 |
| question_answering.md | 11.3 kB | | 1b126820 |
| semantic_segmentation.html | 107 kB | | 15fdab6d |
| semantic_segmentation.md | 21.3 kB | | b7b2e4c3 |
| sequence_classification.html | 53.9 kB | | 1e89d4ad |
| sequence_classification.md | 10.3 kB | | 7ce1c6d0 |
| summarization.html | 60.4 kB | | 2825ae35 |
| summarization.md | 17.7 kB | | 03139a44 |
| text-to-speech.html | 127 kB | | 926860a6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 786655b7 |
| token_classification.md | 13.9 kB | | 72922f24 |
| training_vision_backbone.html | 35.9 kB | | df6cbd56 |
| training_vision_backbone.md | 8.7 kB | | f911bcf9 |
| translation.html | 54.2 kB | | eedca70d |
| translation.md | 10.4 kB | | 3a3f3552 |
| video_classification.html | 89.5 kB | | e91906a4 |
| video_classification.md | 20.8 kB | | 9f85d450 |
| video_text_to_text.html | 25.2 kB | | a4929714 |
| video_text_to_text.md | 6.01 kB | | 0535fccc |
| visual_document_retrieval.html | 27 kB | | 880ecf0c |
| visual_document_retrieval.md | 5.68 kB | | 062dd36a |
| visual_question_answering.html | 69.9 kB | | 685d4622 |
| visual_question_answering.md | 14.8 kB | | de68c14e |
| zero_shot_image_classification.html | 29.7 kB | | d6a14726 |
| zero_shot_image_classification.md | 5.05 kB | | 1e1410c6 |
| zero_shot_object_detection.html | 57.4 kB | | d83ba2f6 |
| zero_shot_object_detection.md | 10.4 kB | | 4361af59 |