| any_to_any.html | 26.9 kB | | cc617d6d |
| any_to_any.md | 4.85 kB | | d9aa3d67 |
| asr.html | 71.4 kB | | 26d3fb72 |
| asr.md | 14.9 kB | | 6e98ce89 |
| audio_classification.html | 65 kB | | 73f41777 |
| audio_classification.md | 12.3 kB | | 46d908ce |
| audio_text_to_text.html | 69.7 kB | | d34ef3ca |
| audio_text_to_text.md | 12.7 kB | | 49bb8f74 |
| document_question_answering.html | 108 kB | | 8de99dae |
| document_question_answering.md | 24.1 kB | | b548d55e |
| image_captioning.html | 49.3 kB | | 45a2e1b5 |
| image_captioning.md | 7.39 kB | | bcff385e |
| image_classification.html | 60.7 kB | | 2b966c2c |
| image_classification.md | 10.9 kB | | d86ef3e3 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | c49735b4 |
| image_text_to_text.md | 17.1 kB | | 0e8a66d0 |
| instance_segmentation.html | 74.1 kB | | 3e51f86c |
| instance_segmentation.md | 18 kB | | 60e6625d |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 19046c49 |
| keypoint_matching.md | 4.4 kB | | 4fc49833 |
| 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 | | a0ff96c4 |
| language_modeling.md | 14 kB | | e3dbaf0e |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 74cc8c62 |
| masked_language_modeling.md | 13.6 kB | | 504ca21b |
| monocular_depth_estimation.html | 29.4 kB | | 16cf0995 |
| monocular_depth_estimation.md | 5.78 kB | | e21fbc8c |
| multiple_choice.html | 51.3 kB | | 97b348f0 |
| multiple_choice.md | 9.41 kB | | 7a9f86c7 |
| object_detection.html | 91.9 kB | | b11ac597 |
| object_detection.md | 22.8 kB | | 80c11d76 |
| prompting.html | 37.1 kB | | a33657e2 |
| prompting.md | 13.4 kB | | 4b71e08d |
| question_answering.html | 54.6 kB | | 74222a35 |
| question_answering.md | 11.3 kB | | 20c57893 |
| semantic_segmentation.html | 107 kB | | 72c360fe |
| semantic_segmentation.md | 21.3 kB | | f547f194 |
| sequence_classification.html | 53.8 kB | | fcb4bab1 |
| sequence_classification.md | 10.3 kB | | 37717ee9 |
| summarization.html | 60.2 kB | | 76befcf1 |
| summarization.md | 17.7 kB | | 541686ed |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 58012167 |
| token_classification.md | 13.9 kB | | 2638ec8c |
| training_vision_backbone.html | 35.8 kB | | b3c32f1d |
| training_vision_backbone.md | 8.7 kB | | 1348dd40 |
| translation.html | 54 kB | | 48c1f9da |
| translation.md | 10.4 kB | | 9b1490e1 |
| video_classification.html | 89.3 kB | | 4a93ff91 |
| video_classification.md | 20.8 kB | | b022e7df |
| video_text_to_text.html | 25.1 kB | | 170a308e |
| video_text_to_text.md | 6.01 kB | | 2b932a84 |
| visual_document_retrieval.html | 26.9 kB | | 947d9a84 |
| visual_document_retrieval.md | 5.68 kB | | aaa552b3 |
| visual_question_answering.html | 69.7 kB | | 7d92c816 |
| visual_question_answering.md | 14.8 kB | | df238fe2 |
| zero_shot_image_classification.html | 29.6 kB | | 7244bb5e |
| zero_shot_image_classification.md | 5.05 kB | | 8b27176c |
| zero_shot_object_detection.html | 57.3 kB | | 7a8d2c5a |
| zero_shot_object_detection.md | 10.4 kB | | e108c119 |