| any_to_any.html | 26.9 kB | | cc4fb3ed |
| any_to_any.md | 4.85 kB | | 9787a706 |
| asr.html | 71.4 kB | | 913a881f |
| asr.md | 14.9 kB | | 0e6d3594 |
| audio_classification.html | 65 kB | | 2997dcff |
| audio_classification.md | 12.3 kB | | 3b3110ea |
| audio_text_to_text.html | 69.7 kB | | 0bd73ba7 |
| audio_text_to_text.md | 12.7 kB | | b1cc350c |
| document_question_answering.html | 108 kB | | 484ca0de |
| document_question_answering.md | 24.1 kB | | bd5a3566 |
| image_captioning.html | 49.3 kB | | 64381ddb |
| image_captioning.md | 7.39 kB | | 528f9e8a |
| image_classification.html | 60.7 kB | | 4b330687 |
| image_classification.md | 10.9 kB | | 7875947d |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 1656b11f |
| image_text_to_text.md | 17.1 kB | | 0c2dadb3 |
| instance_segmentation.html | 74.1 kB | | d12d7091 |
| instance_segmentation.md | 18 kB | | 60766744 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 335ab48b |
| keypoint_matching.md | 4.4 kB | | 9c09662b |
| 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 | | 04d7effe |
| language_modeling.md | 14 kB | | 508f2772 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | f0d76d54 |
| masked_language_modeling.md | 13.6 kB | | 5ec22e0c |
| monocular_depth_estimation.html | 29.4 kB | | 000f8dcf |
| monocular_depth_estimation.md | 5.78 kB | | b0cc41a3 |
| multiple_choice.html | 51.3 kB | | 14024605 |
| multiple_choice.md | 9.41 kB | | 99d54d00 |
| object_detection.html | 91.9 kB | | 142b0b81 |
| object_detection.md | 22.8 kB | | cd3fb1c1 |
| prompting.html | 37.1 kB | | 8f70c883 |
| prompting.md | 13.4 kB | | 2935c601 |
| question_answering.html | 54.6 kB | | 3604a59f |
| question_answering.md | 11.3 kB | | 5958e260 |
| semantic_segmentation.html | 107 kB | | f6311026 |
| semantic_segmentation.md | 21.3 kB | | cf552410 |
| sequence_classification.html | 53.8 kB | | 8ae520ea |
| sequence_classification.md | 10.3 kB | | 5d8ded45 |
| summarization.html | 60.2 kB | | a12a4314 |
| summarization.md | 17.7 kB | | a1267411 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | abeedc5b |
| token_classification.md | 13.9 kB | | 2082ccc4 |
| training_vision_backbone.html | 35.8 kB | | 811af802 |
| training_vision_backbone.md | 8.7 kB | | 9a1513d3 |
| translation.html | 54 kB | | 1de3388a |
| translation.md | 10.4 kB | | 0a00448e |
| video_classification.html | 89.3 kB | | a2e6d682 |
| video_classification.md | 20.8 kB | | 15d9a720 |
| video_text_to_text.html | 25.1 kB | | 857df288 |
| video_text_to_text.md | 6.01 kB | | f63a49db |
| visual_document_retrieval.html | 26.9 kB | | 285de83c |
| visual_document_retrieval.md | 5.68 kB | | 50c8801f |
| visual_question_answering.html | 69.7 kB | | df84660e |
| visual_question_answering.md | 14.8 kB | | ae938485 |
| zero_shot_image_classification.html | 29.6 kB | | 99b65eb3 |
| zero_shot_image_classification.md | 5.05 kB | | 2a72076d |
| zero_shot_object_detection.html | 57.3 kB | | 39324fcc |
| zero_shot_object_detection.md | 10.4 kB | | f7dd2dad |