| any_to_any.html | 26.9 kB | | a1600c69 |
| any_to_any.md | 4.85 kB | | 89cb5e07 |
| asr.html | 71.4 kB | | 5201b10a |
| asr.md | 14.9 kB | | 6673bf6f |
| audio_classification.html | 65 kB | | 46b0a67d |
| audio_classification.md | 12.3 kB | | e7f340f1 |
| audio_text_to_text.html | 69.7 kB | | 1a8de829 |
| audio_text_to_text.md | 12.7 kB | | 1d001d17 |
| document_question_answering.html | 108 kB | | 418ebe57 |
| document_question_answering.md | 24.1 kB | | cccafbe9 |
| image_captioning.html | 49.3 kB | | 00c19b96 |
| image_captioning.md | 7.39 kB | | dec77fe0 |
| image_classification.html | 60.7 kB | | ed68a1ee |
| image_classification.md | 10.9 kB | | 53614a1d |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | afc1d2c6 |
| image_text_to_text.md | 16.7 kB | | 987b9a00 |
| instance_segmentation.html | 74.1 kB | | 65c2d115 |
| instance_segmentation.md | 18 kB | | 626e37c9 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | f4fefa87 |
| keypoint_matching.md | 4.4 kB | | a975dadb |
| 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 | | 91f4d875 |
| language_modeling.md | 14 kB | | 0fa51ec5 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 1e2875a9 |
| masked_language_modeling.md | 13.6 kB | | 8f899b99 |
| monocular_depth_estimation.html | 29.4 kB | | 9faa21aa |
| monocular_depth_estimation.md | 5.78 kB | | bcc1a4f5 |
| multiple_choice.html | 51.3 kB | | d41fad64 |
| multiple_choice.md | 9.41 kB | | 0dbe6d1b |
| object_detection.html | 91.9 kB | | aea50dd5 |
| object_detection.md | 22.8 kB | | c8bbee0c |
| prompting.html | 37.1 kB | | 6e0d576c |
| prompting.md | 13.4 kB | | f964058c |
| question_answering.html | 54.6 kB | | 11875147 |
| question_answering.md | 11.3 kB | | 3c2858a5 |
| semantic_segmentation.html | 107 kB | | 89b4e868 |
| semantic_segmentation.md | 21.3 kB | | b6afe8a9 |
| sequence_classification.html | 53.8 kB | | 0e6c79ba |
| sequence_classification.md | 10.3 kB | | 68c0d465 |
| summarization.html | 60.2 kB | | 1a063214 |
| summarization.md | 17.7 kB | | 5f7fc69f |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | a20f5609 |
| token_classification.md | 13.9 kB | | 171a7d9a |
| training_vision_backbone.html | 35.8 kB | | be59c83c |
| training_vision_backbone.md | 8.7 kB | | 9bd01e9c |
| translation.html | 54 kB | | aa5d8844 |
| translation.md | 10.4 kB | | b088a6d0 |
| video_classification.html | 89.3 kB | | 72f3a1ee |
| video_classification.md | 20.8 kB | | 73abe0c5 |
| video_text_to_text.html | 25.1 kB | | a393091f |
| video_text_to_text.md | 6.01 kB | | c8359e30 |
| visual_document_retrieval.html | 26.9 kB | | 0291be92 |
| visual_document_retrieval.md | 5.68 kB | | 4209a55c |
| visual_question_answering.html | 69.7 kB | | 9982dffa |
| visual_question_answering.md | 14.8 kB | | 4a1024c7 |
| zero_shot_image_classification.html | 29.6 kB | | 793a5039 |
| zero_shot_image_classification.md | 5.05 kB | | 27af498c |
| zero_shot_object_detection.html | 57.3 kB | | 4b0c1acd |
| zero_shot_object_detection.md | 10.4 kB | | ce91d3b8 |