| any_to_any.html | 27 kB | | 119c9406 |
| any_to_any.md | 4.85 kB | | 767da872 |
| asr.html | 71.4 kB | | 7c039f64 |
| asr.md | 14.9 kB | | 5df09c97 |
| audio_classification.html | 65.1 kB | | 9883e26c |
| audio_classification.md | 12.3 kB | | 5f54f375 |
| audio_text_to_text.html | 69.8 kB | | 51c9dd25 |
| audio_text_to_text.md | 12.7 kB | | ff4e68d9 |
| document_question_answering.html | 108 kB | | 027d3744 |
| document_question_answering.md | 24.1 kB | | 82ccab90 |
| image_captioning.html | 49.4 kB | | 8fea811e |
| image_captioning.md | 7.39 kB | | f4d21678 |
| image_classification.html | 60.8 kB | | 8c9d5731 |
| image_classification.md | 10.9 kB | | 13ce81f7 |
| image_feature_extraction.html | 30.5 kB | | 776d0504 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.1 kB | | b023cd4f |
| image_text_to_text.md | 17.1 kB | | ef8cca46 |
| instance_segmentation.html | 74.2 kB | | e102cf0a |
| instance_segmentation.md | 18 kB | | 78cb95b0 |
| keypoint_detection.html | 26 kB | | 311a7cca |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | dc8ceed5 |
| keypoint_matching.md | 4.4 kB | | e19556ab |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 70409f55 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 359d51c7 |
| language_modeling.md | 14 kB | | 482136aa |
| mask_generation.html | 79.9 kB | | b12f48c9 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | ff1aa179 |
| masked_language_modeling.md | 13.6 kB | | 45f20010 |
| monocular_depth_estimation.html | 29.5 kB | | 19c7b080 |
| monocular_depth_estimation.md | 5.78 kB | | 16d8cb6c |
| multiple_choice.html | 51.3 kB | | c7ff9352 |
| multiple_choice.md | 9.41 kB | | ab6503f9 |
| object_detection.html | 91.9 kB | | 82f4eb66 |
| object_detection.md | 22.8 kB | | 94a978ee |
| prompting.html | 37.1 kB | | dc7d25fe |
| prompting.md | 13.4 kB | | b2f3ae91 |
| question_answering.html | 54.7 kB | | b2832e48 |
| question_answering.md | 11.3 kB | | 53405ed1 |
| semantic_segmentation.html | 107 kB | | b06ac557 |
| semantic_segmentation.md | 21.3 kB | | f0794ff0 |
| sequence_classification.html | 53.8 kB | | 938e8c20 |
| sequence_classification.md | 10.3 kB | | 35f15641 |
| summarization.html | 60.3 kB | | 11d0aec3 |
| summarization.md | 17.7 kB | | 27cded20 |
| text-to-speech.html | 127 kB | | bfca3ae8 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 9c690180 |
| token_classification.md | 13.9 kB | | f47654c9 |
| training_vision_backbone.html | 35.9 kB | | 62a0fc38 |
| training_vision_backbone.md | 8.7 kB | | b2f0cca7 |
| translation.html | 54.1 kB | | 19fac27a |
| translation.md | 10.4 kB | | 7ce5d9f5 |
| video_classification.html | 89.4 kB | | 51da8900 |
| video_classification.md | 20.8 kB | | b6b27695 |
| video_text_to_text.html | 25.2 kB | | a58438d7 |
| video_text_to_text.md | 6.01 kB | | d6feb852 |
| visual_document_retrieval.html | 27 kB | | 05a41a05 |
| visual_document_retrieval.md | 5.68 kB | | 782b9b65 |
| visual_question_answering.html | 69.8 kB | | dcb09a27 |
| visual_question_answering.md | 14.8 kB | | 531bff27 |
| zero_shot_image_classification.html | 29.7 kB | | 5f64b0cb |
| zero_shot_image_classification.md | 5.05 kB | | 932f8932 |
| zero_shot_object_detection.html | 57.4 kB | | 02f57ea4 |
| zero_shot_object_detection.md | 10.4 kB | | c37950a2 |