| any_to_any.html | 26.9 kB | | 31d3d780 |
| any_to_any.md | 4.85 kB | | 17214324 |
| asr.html | 71.4 kB | | bb9b6fcc |
| asr.md | 14.9 kB | | 5dec75fb |
| audio_classification.html | 65 kB | | 63ec60ae |
| audio_classification.md | 12.3 kB | | ef1f8e2a |
| audio_text_to_text.html | 69.7 kB | | 8c2ef0a7 |
| audio_text_to_text.md | 12.7 kB | | 67809153 |
| document_question_answering.html | 108 kB | | 16e50fc9 |
| document_question_answering.md | 24.1 kB | | f1f21167 |
| image_captioning.html | 49.3 kB | | aa1d8227 |
| image_captioning.md | 7.39 kB | | e1ecc6fc |
| image_classification.html | 60.7 kB | | 860e3ce2 |
| image_classification.md | 10.9 kB | | c1fa9b1b |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 8ba08157 |
| image_text_to_text.md | 17.1 kB | | 966e7be2 |
| instance_segmentation.html | 74.1 kB | | d9c92e89 |
| instance_segmentation.md | 18 kB | | a949f488 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 895bf2ac |
| keypoint_matching.md | 4.4 kB | | 3d61f197 |
| 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 | | 520a58ee |
| language_modeling.md | 14 kB | | 9ac5fb28 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 64c711e8 |
| masked_language_modeling.md | 13.6 kB | | 80a7823c |
| monocular_depth_estimation.html | 29.4 kB | | ee635a5d |
| monocular_depth_estimation.md | 5.78 kB | | fee1501c |
| multiple_choice.html | 51.3 kB | | 2785cab4 |
| multiple_choice.md | 9.41 kB | | 691649ea |
| object_detection.html | 91.9 kB | | 77eb2b88 |
| object_detection.md | 22.8 kB | | 097943be |
| prompting.html | 37.1 kB | | 13049428 |
| prompting.md | 13.4 kB | | 15a8cc63 |
| question_answering.html | 54.6 kB | | 17baf242 |
| question_answering.md | 11.3 kB | | 780a1383 |
| semantic_segmentation.html | 107 kB | | 17850511 |
| semantic_segmentation.md | 21.3 kB | | 18da25f5 |
| sequence_classification.html | 53.8 kB | | 2369966f |
| sequence_classification.md | 10.3 kB | | a59d9ed6 |
| summarization.html | 60.2 kB | | 27e65246 |
| summarization.md | 17.7 kB | | 1f26b1bc |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | c640e386 |
| token_classification.md | 13.9 kB | | cd472277 |
| training_vision_backbone.html | 35.8 kB | | 214beac4 |
| training_vision_backbone.md | 8.7 kB | | fda8974d |
| translation.html | 54 kB | | 47155636 |
| translation.md | 10.4 kB | | 57ed1478 |
| video_classification.html | 89.3 kB | | 45499915 |
| video_classification.md | 20.8 kB | | 69e14f69 |
| video_text_to_text.html | 25.1 kB | | 35f9f6ca |
| video_text_to_text.md | 6.01 kB | | 4f14e4fc |
| visual_document_retrieval.html | 26.9 kB | | 6742102f |
| visual_document_retrieval.md | 5.68 kB | | 69d16156 |
| visual_question_answering.html | 69.7 kB | | b59cdbe5 |
| visual_question_answering.md | 14.8 kB | | 4cc4c554 |
| zero_shot_image_classification.html | 29.6 kB | | ebf0b92c |
| zero_shot_image_classification.md | 5.05 kB | | 18a0534d |
| zero_shot_object_detection.html | 57.3 kB | | de5c6408 |
| zero_shot_object_detection.md | 10.4 kB | | ba20bbf8 |