| any_to_any.html | 26.9 kB | | 6e6f283a |
| any_to_any.md | 4.85 kB | | 27a6657a |
| asr.html | 71.4 kB | | f6d74444 |
| asr.md | 14.9 kB | | 695379cd |
| audio_classification.html | 65 kB | | e46a7dcf |
| audio_classification.md | 12.3 kB | | 80dec33b |
| audio_text_to_text.html | 69.7 kB | | cecd4730 |
| audio_text_to_text.md | 12.7 kB | | 230638b9 |
| document_question_answering.html | 108 kB | | bff2dd06 |
| document_question_answering.md | 24.1 kB | | a33d8892 |
| image_captioning.html | 49.3 kB | | 0fc70213 |
| image_captioning.md | 7.39 kB | | 0e655ba3 |
| image_classification.html | 60.7 kB | | 2f15b78e |
| image_classification.md | 10.9 kB | | 94c2bf54 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 9b95170a |
| image_text_to_text.md | 16.7 kB | | d9fcdefe |
| instance_segmentation.html | 74.1 kB | | 13de99cd |
| instance_segmentation.md | 18 kB | | ec4bd2f4 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 35da2dd2 |
| keypoint_matching.md | 4.4 kB | | fe783dbd |
| 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 | | dac476d6 |
| language_modeling.md | 14 kB | | d7f13b58 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 31f40f69 |
| masked_language_modeling.md | 13.6 kB | | e08376b3 |
| monocular_depth_estimation.html | 29.4 kB | | dfadd702 |
| monocular_depth_estimation.md | 5.78 kB | | 408a3ff1 |
| multiple_choice.html | 51.3 kB | | 9ca3cc68 |
| multiple_choice.md | 9.41 kB | | cce3e080 |
| object_detection.html | 91.9 kB | | f7129348 |
| object_detection.md | 22.8 kB | | 98e6b84a |
| prompting.html | 37.1 kB | | 38f6754a |
| prompting.md | 13.4 kB | | beca8420 |
| question_answering.html | 54.6 kB | | 2577a17d |
| question_answering.md | 11.3 kB | | 5b21c5e6 |
| semantic_segmentation.html | 107 kB | | 1a2e8d54 |
| semantic_segmentation.md | 21.3 kB | | 291991a8 |
| sequence_classification.html | 53.8 kB | | 7501a2a7 |
| sequence_classification.md | 10.3 kB | | 2925e922 |
| summarization.html | 60.2 kB | | 088ee323 |
| summarization.md | 17.7 kB | | 48c8d926 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | d9f6bddc |
| token_classification.md | 13.9 kB | | f300c4d8 |
| training_vision_backbone.html | 35.8 kB | | adb3c18d |
| training_vision_backbone.md | 8.7 kB | | bf7dedc0 |
| translation.html | 54 kB | | 3f9320b7 |
| translation.md | 10.4 kB | | 377b264f |
| video_classification.html | 89.3 kB | | acf9bce0 |
| video_classification.md | 20.8 kB | | f9fa842f |
| video_text_to_text.html | 25.1 kB | | 6acf2cdc |
| video_text_to_text.md | 6.01 kB | | 8409a9ef |
| visual_document_retrieval.html | 26.9 kB | | 4bc50978 |
| visual_document_retrieval.md | 5.68 kB | | b703bb25 |
| visual_question_answering.html | 69.8 kB | | 45f543d9 |
| visual_question_answering.md | 14.8 kB | | a98454dc |
| zero_shot_image_classification.html | 29.6 kB | | 1fc4ab3b |
| zero_shot_image_classification.md | 5.05 kB | | 0f15adc8 |
| zero_shot_object_detection.html | 57.3 kB | | 4622f536 |
| zero_shot_object_detection.md | 10.4 kB | | e4680322 |