| any_to_any.html | 26.9 kB | | e4833680 |
| any_to_any.md | 4.85 kB | | 6d1948dd |
| asr.html | 71.4 kB | | edd75952 |
| asr.md | 14.9 kB | | f9eb28a2 |
| audio_classification.html | 65 kB | | ab718c9e |
| audio_classification.md | 12.3 kB | | b87cc324 |
| audio_text_to_text.html | 69.7 kB | | 4d7e2b40 |
| audio_text_to_text.md | 12.7 kB | | 3a93be28 |
| document_question_answering.html | 108 kB | | 05b26f06 |
| document_question_answering.md | 24.1 kB | | 8243b0ad |
| image_captioning.html | 49.3 kB | | ec4c1bfd |
| image_captioning.md | 7.39 kB | | ff8ba487 |
| image_classification.html | 60.7 kB | | b9769643 |
| image_classification.md | 10.9 kB | | 736b2221 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | baff818b |
| image_text_to_text.md | 17.1 kB | | 192dd6ec |
| instance_segmentation.html | 74.1 kB | | 782f3afd |
| instance_segmentation.md | 18 kB | | 8e228417 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 301c8d20 |
| keypoint_matching.md | 4.4 kB | | 4ffb1fd7 |
| 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 | | 0daf11e1 |
| language_modeling.md | 14 kB | | 1c02ed37 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 359d8cb4 |
| masked_language_modeling.md | 13.6 kB | | f381b1e1 |
| monocular_depth_estimation.html | 29.4 kB | | 959430db |
| monocular_depth_estimation.md | 5.78 kB | | 88275080 |
| multiple_choice.html | 51.3 kB | | 9c8aadac |
| multiple_choice.md | 9.41 kB | | 0909d39e |
| object_detection.html | 91.9 kB | | 7be16b74 |
| object_detection.md | 22.8 kB | | d8892e80 |
| prompting.html | 37.1 kB | | 7203758e |
| prompting.md | 13.4 kB | | a27ce049 |
| question_answering.html | 54.6 kB | | 5b0190cb |
| question_answering.md | 11.3 kB | | 5de7206f |
| semantic_segmentation.html | 107 kB | | 13ae3d28 |
| semantic_segmentation.md | 21.3 kB | | ec9774a1 |
| sequence_classification.html | 53.8 kB | | 078e991e |
| sequence_classification.md | 10.3 kB | | 9f301a7f |
| summarization.html | 60.2 kB | | ca91081f |
| summarization.md | 17.7 kB | | 869993a6 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 4966272a |
| token_classification.md | 13.9 kB | | 5b51481a |
| training_vision_backbone.html | 35.8 kB | | 92a80e5d |
| training_vision_backbone.md | 8.7 kB | | 2087ea80 |
| translation.html | 54 kB | | 6ff121f2 |
| translation.md | 10.4 kB | | 869672e7 |
| video_classification.html | 89.3 kB | | 6cedf0d0 |
| video_classification.md | 20.8 kB | | eb618b8a |
| video_text_to_text.html | 25.1 kB | | 4ab57ccd |
| video_text_to_text.md | 6.01 kB | | c356e241 |
| visual_document_retrieval.html | 26.9 kB | | 913328c1 |
| visual_document_retrieval.md | 5.68 kB | | 2092611f |
| visual_question_answering.html | 69.7 kB | | 819d0c12 |
| visual_question_answering.md | 14.8 kB | | 4882e95d |
| zero_shot_image_classification.html | 29.6 kB | | c74482b5 |
| zero_shot_image_classification.md | 5.05 kB | | 268145ed |
| zero_shot_object_detection.html | 57.3 kB | | 9406ae4b |
| zero_shot_object_detection.md | 10.4 kB | | 2943161a |