| any_to_any.html | 27 kB | | 8f740e6a |
| any_to_any.md | 4.85 kB | | 224125b4 |
| asr.html | 71.5 kB | | b5a09071 |
| asr.md | 14.9 kB | | d4025a21 |
| audio_classification.html | 65.1 kB | | 3fa360b0 |
| audio_classification.md | 12.3 kB | | 87f9dc6f |
| audio_text_to_text.html | 69.9 kB | | f210673b |
| audio_text_to_text.md | 12.7 kB | | 8fb4949c |
| document_question_answering.html | 108 kB | | faf3aa73 |
| document_question_answering.md | 24.1 kB | | cbacea4f |
| image_captioning.html | 49.5 kB | | ecc5cc44 |
| image_captioning.md | 7.39 kB | | e6dd96b8 |
| image_classification.html | 60.9 kB | | 8eb7c2d3 |
| image_classification.md | 10.9 kB | | 5ba18d1e |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | f7a86c43 |
| image_text_to_text.md | 17.1 kB | | 2324e84c |
| instance_segmentation.html | 74.3 kB | | 5e2a1ff5 |
| instance_segmentation.md | 18 kB | | b2bba249 |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 04995146 |
| keypoint_matching.md | 4.4 kB | | df7ea928 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | fdde2a8b |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | aad171b9 |
| language_modeling.md | 14 kB | | 783347e3 |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 47cc578c |
| masked_language_modeling.md | 13.6 kB | | 6100905b |
| monocular_depth_estimation.html | 29.5 kB | | b0aaac9e |
| monocular_depth_estimation.md | 5.78 kB | | 11636596 |
| multiple_choice.html | 51.4 kB | | 04fdd72a |
| multiple_choice.md | 9.41 kB | | 676bb12e |
| object_detection.html | 92 kB | | 9fc68b88 |
| object_detection.md | 22.8 kB | | d621948b |
| prompting.html | 45.6 kB | | d8652186 |
| prompting.md | 13.4 kB | | 0577bd64 |
| question_answering.html | 54.8 kB | | 05b314a9 |
| question_answering.md | 11.3 kB | | 1b7fa5c8 |
| semantic_segmentation.html | 107 kB | | b624152f |
| semantic_segmentation.md | 21.3 kB | | 21713196 |
| sequence_classification.html | 53.9 kB | | 261d4595 |
| sequence_classification.md | 10.3 kB | | 3c758dea |
| summarization.html | 60.4 kB | | 9f957e30 |
| summarization.md | 17.7 kB | | b9e14112 |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 9b4dac82 |
| token_classification.md | 13.9 kB | | d3624c6c |
| training_vision_backbone.html | 35.9 kB | | f1b0dd26 |
| training_vision_backbone.md | 8.7 kB | | 39e46fe2 |
| translation.html | 54.2 kB | | ec46be9a |
| translation.md | 10.4 kB | | 7cb55e47 |
| video_classification.html | 89.5 kB | | 0ff6e84b |
| video_classification.md | 20.8 kB | | bf432759 |
| video_text_to_text.html | 25.2 kB | | d6c6bc5c |
| video_text_to_text.md | 6.01 kB | | cbfa69db |
| visual_document_retrieval.html | 27 kB | | 482039c2 |
| visual_document_retrieval.md | 5.68 kB | | 72427681 |
| visual_question_answering.html | 69.9 kB | | 11d05832 |
| visual_question_answering.md | 14.8 kB | | d5569e61 |
| zero_shot_image_classification.html | 29.7 kB | | 36548fe6 |
| zero_shot_image_classification.md | 5.05 kB | | 23335b8a |
| zero_shot_object_detection.html | 57.4 kB | | 68e0c428 |
| zero_shot_object_detection.md | 10.4 kB | | 8705f642 |