| any_to_any.html | 26.9 kB | | c0695139 |
| any_to_any.md | 4.85 kB | | 9b869116 |
| asr.html | 71.4 kB | | 570f4587 |
| asr.md | 14.9 kB | | 1d885195 |
| audio_classification.html | 65 kB | | 923135dc |
| audio_classification.md | 12.3 kB | | dfc7655b |
| audio_text_to_text.html | 69.7 kB | | 3c6881c3 |
| audio_text_to_text.md | 12.7 kB | | 70676987 |
| document_question_answering.html | 108 kB | | f78709c2 |
| document_question_answering.md | 24.1 kB | | e64b56b3 |
| image_captioning.html | 49.3 kB | | d86faa38 |
| image_captioning.md | 7.39 kB | | 5394cc92 |
| image_classification.html | 60.7 kB | | 037e1e97 |
| image_classification.md | 10.9 kB | | d2bc46e0 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | b968d96f |
| image_text_to_text.md | 17.1 kB | | 014bb472 |
| instance_segmentation.html | 74.1 kB | | 58cfb964 |
| instance_segmentation.md | 18 kB | | 37043262 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 72ae8f7d |
| keypoint_matching.md | 4.4 kB | | c99d36c4 |
| 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 | | 9509f669 |
| language_modeling.md | 14 kB | | 1e020ec0 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | b59cbc13 |
| masked_language_modeling.md | 13.6 kB | | 2d36d61d |
| monocular_depth_estimation.html | 29.4 kB | | 0efa1768 |
| monocular_depth_estimation.md | 5.78 kB | | d3add464 |
| multiple_choice.html | 51.3 kB | | 93bdd404 |
| multiple_choice.md | 9.41 kB | | 34078610 |
| object_detection.html | 91.9 kB | | 08b5d21a |
| object_detection.md | 22.8 kB | | ff61ecdc |
| prompting.html | 37.1 kB | | d8031601 |
| prompting.md | 13.4 kB | | 9395510a |
| question_answering.html | 54.6 kB | | 22399532 |
| question_answering.md | 11.3 kB | | e4bfb0e5 |
| semantic_segmentation.html | 107 kB | | 4bf37e99 |
| semantic_segmentation.md | 21.3 kB | | 7631dcbc |
| sequence_classification.html | 53.8 kB | | 172e44bf |
| sequence_classification.md | 10.3 kB | | ef631a37 |
| summarization.html | 60.2 kB | | 5ec925d6 |
| summarization.md | 17.7 kB | | 919753c0 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 78515c93 |
| token_classification.md | 13.9 kB | | 5a80a5b7 |
| training_vision_backbone.html | 35.8 kB | | fda8633d |
| training_vision_backbone.md | 8.7 kB | | 63ee7049 |
| translation.html | 54 kB | | a77072ea |
| translation.md | 10.4 kB | | d07a7e97 |
| video_classification.html | 89.3 kB | | 3772726e |
| video_classification.md | 20.8 kB | | f9fad7b2 |
| video_text_to_text.html | 25.1 kB | | c10b49ed |
| video_text_to_text.md | 6.01 kB | | d9bf6440 |
| visual_document_retrieval.html | 26.9 kB | | ef3e078a |
| visual_document_retrieval.md | 5.68 kB | | 53f44fc5 |
| visual_question_answering.html | 69.7 kB | | 28a8a74d |
| visual_question_answering.md | 14.8 kB | | cb674b15 |
| zero_shot_image_classification.html | 29.6 kB | | 10313b10 |
| zero_shot_image_classification.md | 5.05 kB | | 43bd03e7 |
| zero_shot_object_detection.html | 57.3 kB | | b95f742e |
| zero_shot_object_detection.md | 10.4 kB | | 0e87b839 |