| any_to_any.html | 26.9 kB | | df348c53 |
| any_to_any.md | 4.85 kB | | e6e94dc5 |
| asr.html | 71.4 kB | | f4b70360 |
| asr.md | 14.9 kB | | baf46011 |
| audio_classification.html | 65 kB | | 026eb598 |
| audio_classification.md | 12.3 kB | | 95f9432a |
| audio_text_to_text.html | 69.7 kB | | 6064fa22 |
| audio_text_to_text.md | 12.7 kB | | 293c9e2f |
| document_question_answering.html | 108 kB | | 9e5fd23c |
| document_question_answering.md | 24.1 kB | | e1e9c813 |
| image_captioning.html | 49.3 kB | | 3862bfa5 |
| image_captioning.md | 7.39 kB | | 6e159e1c |
| image_classification.html | 60.7 kB | | 0e06f285 |
| image_classification.md | 10.9 kB | | 354efd9f |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | bf71cac0 |
| image_text_to_text.md | 16.7 kB | | d7ad7e11 |
| instance_segmentation.html | 74.1 kB | | 1cd11aea |
| instance_segmentation.md | 18 kB | | 7ed97f7a |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | dcd749ac |
| keypoint_matching.md | 4.4 kB | | 2364c1a4 |
| 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 | | a60bb142 |
| language_modeling.md | 14 kB | | bba0dfc9 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 2102847e |
| masked_language_modeling.md | 13.6 kB | | 1fdbd1fc |
| monocular_depth_estimation.html | 29.4 kB | | d53f6cc0 |
| monocular_depth_estimation.md | 5.78 kB | | 7ecbffa0 |
| multiple_choice.html | 51.3 kB | | bb15319e |
| multiple_choice.md | 9.41 kB | | 92271149 |
| object_detection.html | 91.9 kB | | a1e7ad42 |
| object_detection.md | 22.8 kB | | 2464b9c1 |
| prompting.html | 37.1 kB | | 21b954f1 |
| prompting.md | 13.4 kB | | d531d505 |
| question_answering.html | 54.6 kB | | af996551 |
| question_answering.md | 11.3 kB | | 02e01380 |
| semantic_segmentation.html | 107 kB | | 5efb195b |
| semantic_segmentation.md | 21.3 kB | | ce1d4edd |
| sequence_classification.html | 53.8 kB | | 44c3f1df |
| sequence_classification.md | 10.3 kB | | ba6d6146 |
| summarization.html | 60.2 kB | | 386e265b |
| summarization.md | 17.7 kB | | 1ea92f73 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 2ae55dc1 |
| token_classification.md | 13.9 kB | | 9b702667 |
| training_vision_backbone.html | 35.8 kB | | 20cb6be0 |
| training_vision_backbone.md | 8.7 kB | | c2f4be7f |
| translation.html | 54 kB | | 34482fc3 |
| translation.md | 10.4 kB | | ccabefd3 |
| video_classification.html | 89.3 kB | | 49eae226 |
| video_classification.md | 20.8 kB | | b90e2589 |
| video_text_to_text.html | 25.1 kB | | 67134c93 |
| video_text_to_text.md | 6.01 kB | | 719628d7 |
| visual_document_retrieval.html | 26.9 kB | | 734496ed |
| visual_document_retrieval.md | 5.68 kB | | 3536a4e6 |
| visual_question_answering.html | 69.8 kB | | 4076c924 |
| visual_question_answering.md | 14.8 kB | | 63ee53ff |
| zero_shot_image_classification.html | 29.6 kB | | 75bf2033 |
| zero_shot_image_classification.md | 5.05 kB | | ae10882b |
| zero_shot_object_detection.html | 57.3 kB | | 3386616c |
| zero_shot_object_detection.md | 10.4 kB | | 17111f47 |