| any_to_any.html | 26.9 kB | | a210a855 |
| any_to_any.md | 4.85 kB | | ec745e26 |
| asr.html | 71.4 kB | | 92e7cc95 |
| asr.md | 14.9 kB | | c50ddd7b |
| audio_classification.html | 65 kB | | f7760531 |
| audio_classification.md | 12.3 kB | | e0a41ac3 |
| audio_text_to_text.html | 69.7 kB | | 0afdde2e |
| audio_text_to_text.md | 12.7 kB | | 796d9d3e |
| document_question_answering.html | 108 kB | | d3f2dced |
| document_question_answering.md | 24.1 kB | | f03ea961 |
| image_captioning.html | 49.3 kB | | ad0d66d3 |
| image_captioning.md | 7.39 kB | | 54bb4915 |
| image_classification.html | 60.7 kB | | 9f9b8537 |
| image_classification.md | 10.9 kB | | 77e7752d |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | ca48fbf4 |
| image_text_to_text.md | 17.1 kB | | f049e719 |
| instance_segmentation.html | 74.1 kB | | b3e1891f |
| instance_segmentation.md | 18 kB | | d97e41b2 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | d203266c |
| keypoint_matching.md | 4.4 kB | | a3ce6894 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 234bf223 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.4 kB | | d56ed98f |
| language_modeling.md | 14 kB | | f2508b94 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 92c2431c |
| masked_language_modeling.md | 13.6 kB | | cd958698 |
| monocular_depth_estimation.html | 29.4 kB | | 3524499d |
| monocular_depth_estimation.md | 5.78 kB | | 9df9f311 |
| multiple_choice.html | 51.3 kB | | fc9dbee2 |
| multiple_choice.md | 9.41 kB | | 6126a471 |
| object_detection.html | 91.9 kB | | 91535c21 |
| object_detection.md | 22.8 kB | | f16fee01 |
| prompting.html | 37.1 kB | | 5386911a |
| prompting.md | 13.4 kB | | 07443be9 |
| question_answering.html | 54.6 kB | | c8f8923a |
| question_answering.md | 11.3 kB | | 2955ec60 |
| semantic_segmentation.html | 107 kB | | f8229858 |
| semantic_segmentation.md | 21.3 kB | | 2534afcc |
| sequence_classification.html | 53.8 kB | | b9399ccb |
| sequence_classification.md | 10.3 kB | | 78ff504a |
| summarization.html | 60.2 kB | | d24602c4 |
| summarization.md | 17.7 kB | | 0971afed |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | cd6353d2 |
| token_classification.md | 13.9 kB | | d10a5ec7 |
| training_vision_backbone.html | 35.8 kB | | fcbcdf18 |
| training_vision_backbone.md | 8.7 kB | | 650a2cec |
| translation.html | 54 kB | | 4f6fbf9f |
| translation.md | 10.4 kB | | a804bed5 |
| video_classification.html | 89.3 kB | | 80429a55 |
| video_classification.md | 20.8 kB | | 048758cf |
| video_text_to_text.html | 25.1 kB | | 413908a7 |
| video_text_to_text.md | 6.01 kB | | 86555f6e |
| visual_document_retrieval.html | 26.9 kB | | 0637862c |
| visual_document_retrieval.md | 5.68 kB | | 1e750d7f |
| visual_question_answering.html | 69.7 kB | | 95c47ad8 |
| visual_question_answering.md | 14.8 kB | | df6ec71e |
| zero_shot_image_classification.html | 29.6 kB | | 8a7fc3b1 |
| zero_shot_image_classification.md | 5.05 kB | | f4252e12 |
| zero_shot_object_detection.html | 57.3 kB | | 1efc385f |
| zero_shot_object_detection.md | 10.4 kB | | 476cc81a |