| any_to_any.html | 26.9 kB | | 9a6b1f5e |
| any_to_any.md | 4.85 kB | | e5d64b4b |
| asr.html | 71.4 kB | | 303aefca |
| asr.md | 14.9 kB | | 569a7113 |
| audio_classification.html | 65 kB | | c2e9363b |
| audio_classification.md | 12.3 kB | | 09a377cf |
| audio_text_to_text.html | 69.7 kB | | 8d079235 |
| audio_text_to_text.md | 12.7 kB | | d7204fd5 |
| document_question_answering.html | 108 kB | | b7ed53fe |
| document_question_answering.md | 24.1 kB | | 644e2e6c |
| image_captioning.html | 49.3 kB | | 8609fdb2 |
| image_captioning.md | 7.39 kB | | 72348bfb |
| image_classification.html | 60.7 kB | | 5d3af7f6 |
| image_classification.md | 10.9 kB | | de8076c2 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 2419961c |
| image_text_to_text.md | 17.1 kB | | 470025ee |
| instance_segmentation.html | 74.1 kB | | 7825318c |
| instance_segmentation.md | 18 kB | | b161f85d |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 6a0e145e |
| keypoint_matching.md | 4.4 kB | | 8f37634b |
| 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 | | 3c252db2 |
| language_modeling.md | 14 kB | | fc0239a9 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | b3345922 |
| masked_language_modeling.md | 13.6 kB | | d40c64d8 |
| monocular_depth_estimation.html | 29.4 kB | | 0231ade8 |
| monocular_depth_estimation.md | 5.78 kB | | 990c6352 |
| multiple_choice.html | 51.3 kB | | 69e2b1bd |
| multiple_choice.md | 9.41 kB | | 19775afe |
| object_detection.html | 91.9 kB | | bee347e3 |
| object_detection.md | 22.8 kB | | 2113ab95 |
| prompting.html | 37.1 kB | | 0c2e1ce6 |
| prompting.md | 13.4 kB | | 753bd1af |
| question_answering.html | 54.6 kB | | ff1f28c5 |
| question_answering.md | 11.3 kB | | a7bf236a |
| semantic_segmentation.html | 107 kB | | d71d6f5f |
| semantic_segmentation.md | 21.3 kB | | 8a0b35fd |
| sequence_classification.html | 53.8 kB | | 85ebd6d4 |
| sequence_classification.md | 10.3 kB | | 0495f646 |
| summarization.html | 60.2 kB | | 676f9fd2 |
| summarization.md | 17.7 kB | | 660b3956 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 73b4946d |
| token_classification.md | 13.9 kB | | d22d9012 |
| training_vision_backbone.html | 35.8 kB | | b556bd7a |
| training_vision_backbone.md | 8.7 kB | | 3fd26b4f |
| translation.html | 54 kB | | a76ff634 |
| translation.md | 10.4 kB | | 18da351c |
| video_classification.html | 89.3 kB | | 38a13bc2 |
| video_classification.md | 20.8 kB | | c775f7d2 |
| video_text_to_text.html | 25.1 kB | | 5bc31556 |
| video_text_to_text.md | 6.01 kB | | 0bcd7f9a |
| visual_document_retrieval.html | 26.9 kB | | 33ec1fc6 |
| visual_document_retrieval.md | 5.68 kB | | cc620868 |
| visual_question_answering.html | 69.7 kB | | 2e979322 |
| visual_question_answering.md | 14.8 kB | | ca61e694 |
| zero_shot_image_classification.html | 29.6 kB | | b8ab822c |
| zero_shot_image_classification.md | 5.05 kB | | be1c4f1b |
| zero_shot_object_detection.html | 57.3 kB | | d85768ff |
| zero_shot_object_detection.md | 10.4 kB | | a140d207 |