| any_to_any.html | 26.9 kB | | cea2047c |
| any_to_any.md | 4.85 kB | | 350b0ad5 |
| asr.html | 71.4 kB | | b0385b6a |
| asr.md | 14.9 kB | | 92cec21f |
| audio_classification.html | 65 kB | | fafc15d2 |
| audio_classification.md | 12.3 kB | | 0830b768 |
| audio_text_to_text.html | 69.7 kB | | 3fe9fc11 |
| audio_text_to_text.md | 12.7 kB | | 5006be98 |
| document_question_answering.html | 108 kB | | 183c03a4 |
| document_question_answering.md | 24.1 kB | | dbee46db |
| image_captioning.html | 49.3 kB | | bf8749a4 |
| image_captioning.md | 7.39 kB | | c08fe549 |
| image_classification.html | 60.7 kB | | 07f355e5 |
| image_classification.md | 10.9 kB | | fcc4ddfe |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | a517cdea |
| image_text_to_text.md | 17.1 kB | | 09ab40c8 |
| instance_segmentation.html | 74.1 kB | | faeabcd4 |
| instance_segmentation.md | 18 kB | | 38d119d6 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | d14cb099 |
| keypoint_matching.md | 4.4 kB | | 381e705e |
| 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 | | 5080322a |
| language_modeling.md | 14 kB | | 3f4a5bf3 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 096ac633 |
| masked_language_modeling.md | 13.6 kB | | 9ce1ada2 |
| monocular_depth_estimation.html | 29.4 kB | | 6df570dd |
| monocular_depth_estimation.md | 5.78 kB | | ceed3535 |
| multiple_choice.html | 51.3 kB | | 95ed9358 |
| multiple_choice.md | 9.41 kB | | 6d23ae56 |
| object_detection.html | 91.9 kB | | 00585a6b |
| object_detection.md | 22.8 kB | | 77257bef |
| prompting.html | 37.1 kB | | bc1aaeb1 |
| prompting.md | 13.4 kB | | 046e4b75 |
| question_answering.html | 54.6 kB | | 69ffaa8a |
| question_answering.md | 11.3 kB | | 6264f1dc |
| semantic_segmentation.html | 107 kB | | 6e677880 |
| semantic_segmentation.md | 21.3 kB | | e86b0ef2 |
| sequence_classification.html | 53.8 kB | | 986ec9e9 |
| sequence_classification.md | 10.3 kB | | 686c68d4 |
| summarization.html | 60.2 kB | | b2fecf29 |
| summarization.md | 17.7 kB | | d3cda76c |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 1424ba0c |
| token_classification.md | 13.9 kB | | 964ae17c |
| training_vision_backbone.html | 35.8 kB | | afd45e8d |
| training_vision_backbone.md | 8.7 kB | | e8fdebd3 |
| translation.html | 54 kB | | 1db78aa0 |
| translation.md | 10.4 kB | | 7147dddb |
| video_classification.html | 89.3 kB | | 4e9fee4a |
| video_classification.md | 20.8 kB | | 2a327ce8 |
| video_text_to_text.html | 25.1 kB | | a0c4b33b |
| video_text_to_text.md | 6.01 kB | | 5e34a2bd |
| visual_document_retrieval.html | 26.9 kB | | 53da3a59 |
| visual_document_retrieval.md | 5.68 kB | | 33fd34d8 |
| visual_question_answering.html | 69.7 kB | | c4015db0 |
| visual_question_answering.md | 14.8 kB | | a46bf458 |
| zero_shot_image_classification.html | 29.6 kB | | e32ddc59 |
| zero_shot_image_classification.md | 5.05 kB | | 38e73d5a |
| zero_shot_object_detection.html | 57.3 kB | | d285c1c3 |
| zero_shot_object_detection.md | 10.4 kB | | e776e1c1 |