| any_to_any.html | 26.9 kB | | afc202f2 |
| any_to_any.md | 4.85 kB | | a39fa872 |
| asr.html | 71.4 kB | | 81f0a9db |
| asr.md | 14.9 kB | | 974c6197 |
| audio_classification.html | 65 kB | | 68b6f5f4 |
| audio_classification.md | 12.3 kB | | 9000eb2a |
| audio_text_to_text.html | 69.7 kB | | fa00b2d6 |
| audio_text_to_text.md | 12.7 kB | | c10b6a46 |
| document_question_answering.html | 108 kB | | 4c37e172 |
| document_question_answering.md | 24.1 kB | | 38ba16af |
| image_captioning.html | 49.3 kB | | c6bd6169 |
| image_captioning.md | 7.39 kB | | f36611b2 |
| image_classification.html | 60.7 kB | | 8065ec3b |
| image_classification.md | 10.9 kB | | cc23060c |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 6d6cf0a4 |
| image_text_to_text.md | 16.7 kB | | e04f3980 |
| instance_segmentation.html | 74.1 kB | | 1cf52bea |
| instance_segmentation.md | 18 kB | | e9cb6a3c |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | c24998c6 |
| keypoint_matching.md | 4.4 kB | | 6fdb843b |
| 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 | | a32a0288 |
| language_modeling.md | 14 kB | | e414ce3a |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 789083e9 |
| masked_language_modeling.md | 13.6 kB | | 22956038 |
| monocular_depth_estimation.html | 29.4 kB | | f903ca56 |
| monocular_depth_estimation.md | 5.78 kB | | 7db2b9af |
| multiple_choice.html | 51.3 kB | | f9f3d576 |
| multiple_choice.md | 9.41 kB | | 1054403a |
| object_detection.html | 91.9 kB | | e287a5ec |
| object_detection.md | 22.8 kB | | 17596eea |
| prompting.html | 37.1 kB | | bf735f14 |
| prompting.md | 13.4 kB | | b51baa16 |
| question_answering.html | 54.6 kB | | 033c3361 |
| question_answering.md | 11.3 kB | | 53500242 |
| semantic_segmentation.html | 107 kB | | 246711d0 |
| semantic_segmentation.md | 21.3 kB | | 94686658 |
| sequence_classification.html | 53.8 kB | | bb5f1b95 |
| sequence_classification.md | 10.3 kB | | 9fb16810 |
| summarization.html | 60.2 kB | | 1d5f30c0 |
| summarization.md | 17.7 kB | | f8c0eec4 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 9b5af1f7 |
| token_classification.md | 13.9 kB | | 58b64d47 |
| training_vision_backbone.html | 35.8 kB | | 476d7f62 |
| training_vision_backbone.md | 8.7 kB | | 96c10931 |
| translation.html | 54 kB | | ee8124ce |
| translation.md | 10.4 kB | | b6e2c15c |
| video_classification.html | 89.3 kB | | e182aa71 |
| video_classification.md | 20.8 kB | | 92bd3ef5 |
| video_text_to_text.html | 25.1 kB | | ad7f8f69 |
| video_text_to_text.md | 6.01 kB | | 41717cce |
| visual_document_retrieval.html | 26.9 kB | | a7e4844e |
| visual_document_retrieval.md | 5.68 kB | | 16d86549 |
| visual_question_answering.html | 69.7 kB | | 8991a170 |
| visual_question_answering.md | 14.8 kB | | e1277ebd |
| zero_shot_image_classification.html | 29.6 kB | | db08f33a |
| zero_shot_image_classification.md | 5.05 kB | | 200daa0f |
| zero_shot_object_detection.html | 57.3 kB | | c6f93d8e |
| zero_shot_object_detection.md | 10.4 kB | | 9b1298b9 |