| any_to_any.html | 27 kB | | 6c0eb9a9 |
| any_to_any.md | 4.85 kB | | 787648e5 |
| asr.html | 71.5 kB | | 1ac09284 |
| asr.md | 14.9 kB | | 7b51a8f0 |
| audio_classification.html | 65.2 kB | | 467910f1 |
| audio_classification.md | 12.3 kB | | c2678bd3 |
| audio_text_to_text.html | 69.9 kB | | f60995a6 |
| audio_text_to_text.md | 12.7 kB | | d69b3502 |
| document_question_answering.html | 108 kB | | cb39b6df |
| document_question_answering.md | 24.1 kB | | 646d6961 |
| image_captioning.html | 49.5 kB | | 337296a6 |
| image_captioning.md | 7.39 kB | | 25368b00 |
| image_classification.html | 60.9 kB | | c0a9c97e |
| image_classification.md | 10.9 kB | | 7f2b9f5e |
| image_feature_extraction.html | 30.5 kB | | eede085f |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | b803b07c |
| image_text_to_text.md | 17.1 kB | | ae83cb04 |
| instance_segmentation.html | 74.3 kB | | c4f64874 |
| instance_segmentation.md | 18 kB | | 048e7621 |
| keypoint_detection.html | 26 kB | | bfa5115d |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 40449b8d |
| keypoint_matching.md | 4.4 kB | | 63645758 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | d3943efb |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 8a2eec4e |
| language_modeling.md | 14 kB | | 1cb6155a |
| mask_generation.html | 80 kB | | 4fbc2918 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 2e34cc79 |
| masked_language_modeling.md | 13.6 kB | | 18e8e89d |
| monocular_depth_estimation.html | 29.5 kB | | 2e43b7c8 |
| monocular_depth_estimation.md | 5.78 kB | | 552e559c |
| multiple_choice.html | 51.4 kB | | c0ca37f0 |
| multiple_choice.md | 9.41 kB | | ae349fc4 |
| object_detection.html | 92 kB | | 5f6d6ba2 |
| object_detection.md | 22.8 kB | | b3d5f512 |
| prompting.html | 45.6 kB | | a201a34e |
| prompting.md | 13.4 kB | | cdc7937f |
| question_answering.html | 54.8 kB | | 387b8c55 |
| question_answering.md | 11.3 kB | | 7b9e9d7a |
| semantic_segmentation.html | 107 kB | | 6fb6e99f |
| semantic_segmentation.md | 21.3 kB | | f2353f7d |
| sequence_classification.html | 53.9 kB | | 4716e0ec |
| sequence_classification.md | 10.3 kB | | 0fa3b9d8 |
| summarization.html | 60.4 kB | | ae5f5a3f |
| summarization.md | 17.7 kB | | 4b7e2e33 |
| text-to-speech.html | 127 kB | | 06bf12d6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 81e0f186 |
| token_classification.md | 13.9 kB | | a2184eeb |
| training_vision_backbone.html | 35.9 kB | | dcc09e7a |
| training_vision_backbone.md | 8.7 kB | | b29044c6 |
| translation.html | 54.2 kB | | cb44c594 |
| translation.md | 10.4 kB | | 19b7514f |
| video_classification.html | 89.5 kB | | f47e4d5f |
| video_classification.md | 20.8 kB | | cd33caf7 |
| video_text_to_text.html | 25.2 kB | | 9237ba6a |
| video_text_to_text.md | 6.01 kB | | 01d7d617 |
| visual_document_retrieval.html | 27 kB | | 6f47f74f |
| visual_document_retrieval.md | 5.68 kB | | ab17b969 |
| visual_question_answering.html | 69.9 kB | | 1e997c18 |
| visual_question_answering.md | 14.8 kB | | 54ff6f1d |
| zero_shot_image_classification.html | 29.7 kB | | 61feaa15 |
| zero_shot_image_classification.md | 5.05 kB | | bb6d16c9 |
| zero_shot_object_detection.html | 57.4 kB | | d5990528 |
| zero_shot_object_detection.md | 10.4 kB | | 380de253 |