| any_to_any.html | 26.9 kB | | 2e1f2e32 |
| any_to_any.md | 4.85 kB | | d1b3c224 |
| asr.html | 71.4 kB | | c1fe768c |
| asr.md | 14.9 kB | | 4e5eeb63 |
| audio_classification.html | 65 kB | | 70b41031 |
| audio_classification.md | 12.3 kB | | 872f7286 |
| audio_text_to_text.html | 69.7 kB | | 778ceecc |
| audio_text_to_text.md | 12.7 kB | | 571997e8 |
| document_question_answering.html | 108 kB | | 074bc745 |
| document_question_answering.md | 24.1 kB | | f30e507e |
| image_captioning.html | 49.3 kB | | 252c18c0 |
| image_captioning.md | 7.39 kB | | bb2a0ec1 |
| image_classification.html | 60.7 kB | | 448f3231 |
| image_classification.md | 10.9 kB | | 6f7cccad |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | cd1a4045 |
| image_text_to_text.md | 17.1 kB | | 88ccdfcb |
| instance_segmentation.html | 74.1 kB | | 0a09c96b |
| instance_segmentation.md | 18 kB | | 03ce04ef |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 2c7be5b6 |
| keypoint_matching.md | 4.4 kB | | e2626da3 |
| 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 | | 2661646b |
| language_modeling.md | 14 kB | | bde09f22 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 80f11f73 |
| masked_language_modeling.md | 13.6 kB | | 8fcc2eec |
| monocular_depth_estimation.html | 29.4 kB | | 8fd04706 |
| monocular_depth_estimation.md | 5.78 kB | | 320649b1 |
| multiple_choice.html | 51.3 kB | | cdaecab0 |
| multiple_choice.md | 9.41 kB | | 24b483ae |
| object_detection.html | 91.9 kB | | 799e1fdc |
| object_detection.md | 22.8 kB | | 6e2c5687 |
| prompting.html | 37.1 kB | | bdbd9055 |
| prompting.md | 13.4 kB | | f79a8cf5 |
| question_answering.html | 54.6 kB | | ebef4ca1 |
| question_answering.md | 11.3 kB | | 1dd2370e |
| semantic_segmentation.html | 107 kB | | 966efe0b |
| semantic_segmentation.md | 21.3 kB | | 40670b3a |
| sequence_classification.html | 53.8 kB | | f6db81ca |
| sequence_classification.md | 10.3 kB | | 981d260c |
| summarization.html | 60.2 kB | | b3cfd48c |
| summarization.md | 17.7 kB | | 8d2c3770 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 37576935 |
| token_classification.md | 13.9 kB | | 2675b585 |
| training_vision_backbone.html | 35.8 kB | | 51d435fa |
| training_vision_backbone.md | 8.7 kB | | a8979fb5 |
| translation.html | 54 kB | | 88e12c71 |
| translation.md | 10.4 kB | | 118c775d |
| video_classification.html | 89.3 kB | | 4ede9cef |
| video_classification.md | 20.8 kB | | 36aaaf9a |
| video_text_to_text.html | 25.1 kB | | f8275bef |
| video_text_to_text.md | 6.01 kB | | b29dd23d |
| visual_document_retrieval.html | 26.9 kB | | da246236 |
| visual_document_retrieval.md | 5.68 kB | | d1977405 |
| visual_question_answering.html | 69.7 kB | | 2e367681 |
| visual_question_answering.md | 14.8 kB | | 7b175cf8 |
| zero_shot_image_classification.html | 29.6 kB | | e792becd |
| zero_shot_image_classification.md | 5.05 kB | | cd226302 |
| zero_shot_object_detection.html | 57.3 kB | | 5b9af293 |
| zero_shot_object_detection.md | 10.4 kB | | 6e7c7c7e |