| any_to_any.html | 27 kB | | 341ee45a |
| any_to_any.md | 4.85 kB | | 0a146b4f |
| asr.html | 71.5 kB | | 7f89739a |
| asr.md | 14.9 kB | | 4b2897d6 |
| audio_classification.html | 65.2 kB | | 1f6a6184 |
| audio_classification.md | 12.3 kB | | bef9b645 |
| audio_text_to_text.html | 69.9 kB | | 4c7861e2 |
| audio_text_to_text.md | 12.7 kB | | 729f403c |
| document_question_answering.html | 108 kB | | ffe54f07 |
| document_question_answering.md | 24.1 kB | | 15eb9d25 |
| image_captioning.html | 49.5 kB | | 5481eab1 |
| image_captioning.md | 7.39 kB | | ed9920f9 |
| image_classification.html | 60.9 kB | | 7a7b35c7 |
| image_classification.md | 10.9 kB | | e1cd17a8 |
| image_feature_extraction.html | 30.5 kB | | 35f6dc51 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | 20e6a769 |
| image_text_to_text.md | 17.1 kB | | c4a8e123 |
| instance_segmentation.html | 74.3 kB | | 35f66ff9 |
| instance_segmentation.md | 18 kB | | bfac1570 |
| keypoint_detection.html | 26 kB | | b27ebc03 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | ee4090f7 |
| keypoint_matching.md | 4.4 kB | | 3d65527a |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 2d6feaf2 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 6ee7d98c |
| language_modeling.md | 14 kB | | 825c76d9 |
| mask_generation.html | 80 kB | | 3403429a |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | e08eb11e |
| masked_language_modeling.md | 13.6 kB | | 2f9e5cdc |
| monocular_depth_estimation.html | 29.5 kB | | 54fca44a |
| monocular_depth_estimation.md | 5.78 kB | | 1bfa0595 |
| multiple_choice.html | 51.4 kB | | 474a666c |
| multiple_choice.md | 9.41 kB | | 916ce25a |
| object_detection.html | 92 kB | | 8dec475a |
| object_detection.md | 22.8 kB | | e11cd299 |
| prompting.html | 45.6 kB | | 15820dfb |
| prompting.md | 13.4 kB | | c33e4be8 |
| question_answering.html | 54.8 kB | | 33b12830 |
| question_answering.md | 11.3 kB | | 0f6d27c6 |
| semantic_segmentation.html | 107 kB | | f4465af5 |
| semantic_segmentation.md | 21.3 kB | | c9bec0ec |
| sequence_classification.html | 53.9 kB | | 6f6b7dad |
| sequence_classification.md | 10.3 kB | | 97c45930 |
| summarization.html | 60.4 kB | | c82243b3 |
| summarization.md | 17.7 kB | | ab395e96 |
| text-to-speech.html | 127 kB | | 926860a6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 2013b0e4 |
| token_classification.md | 13.9 kB | | 5a66400c |
| training_vision_backbone.html | 35.9 kB | | 1ae9ac98 |
| training_vision_backbone.md | 8.7 kB | | 8bd7d62b |
| translation.html | 54.2 kB | | e73ab75d |
| translation.md | 10.4 kB | | 4caf68b0 |
| video_classification.html | 89.5 kB | | 7084704d |
| video_classification.md | 20.8 kB | | d161b46f |
| video_text_to_text.html | 25.2 kB | | 9f444296 |
| video_text_to_text.md | 6.01 kB | | 144c3918 |
| visual_document_retrieval.html | 27 kB | | b5c0ded2 |
| visual_document_retrieval.md | 5.68 kB | | aad46d30 |
| visual_question_answering.html | 69.9 kB | | 86517b3c |
| visual_question_answering.md | 14.8 kB | | 7c6cc402 |
| zero_shot_image_classification.html | 29.7 kB | | 23996ebf |
| zero_shot_image_classification.md | 5.05 kB | | 84e51711 |
| zero_shot_object_detection.html | 57.4 kB | | 48af87ab |
| zero_shot_object_detection.md | 10.4 kB | | 611ff86b |