| any_to_any.html | 27 kB | | f898503e |
| any_to_any.md | 4.85 kB | | 4c96216d |
| asr.html | 71.5 kB | | 312fdcee |
| asr.md | 14.9 kB | | 0a81173e |
| audio_classification.html | 65.2 kB | | 835c0158 |
| audio_classification.md | 12.3 kB | | 19322a7b |
| audio_text_to_text.html | 69.9 kB | | 4f95244f |
| audio_text_to_text.md | 12.7 kB | | 96255b8a |
| document_question_answering.html | 108 kB | | 4b49bd7b |
| document_question_answering.md | 24.1 kB | | f6f3e493 |
| image_captioning.html | 49.5 kB | | eaebc242 |
| image_captioning.md | 7.39 kB | | 5ef94d4c |
| image_classification.html | 60.9 kB | | a1a83907 |
| image_classification.md | 10.9 kB | | 33324c11 |
| image_feature_extraction.html | 30.5 kB | | 35f6dc51 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | 980302ba |
| image_text_to_text.md | 17.1 kB | | c72a10d3 |
| instance_segmentation.html | 74.3 kB | | d809495a |
| instance_segmentation.md | 18 kB | | abc9d48d |
| keypoint_detection.html | 26 kB | | b27ebc03 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 64c76a7b |
| keypoint_matching.md | 4.4 kB | | 183aba96 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 2d6feaf2 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 45cdae7e |
| language_modeling.md | 14 kB | | 6170c4a4 |
| mask_generation.html | 80 kB | | 3403429a |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 0020a75f |
| masked_language_modeling.md | 13.6 kB | | 8f08eef5 |
| monocular_depth_estimation.html | 29.5 kB | | 81d1ca4d |
| monocular_depth_estimation.md | 5.78 kB | | 6a39e061 |
| multiple_choice.html | 51.4 kB | | 2869ed8d |
| multiple_choice.md | 9.41 kB | | 6674c853 |
| object_detection.html | 92 kB | | 2b338e52 |
| object_detection.md | 22.8 kB | | 3d525a52 |
| prompting.html | 45.6 kB | | fde1abc6 |
| prompting.md | 13.4 kB | | ca5d7ec1 |
| question_answering.html | 54.8 kB | | b28ede55 |
| question_answering.md | 11.3 kB | | 370e419b |
| semantic_segmentation.html | 107 kB | | 23fd2554 |
| semantic_segmentation.md | 21.3 kB | | 0006f6f9 |
| sequence_classification.html | 53.9 kB | | 4ef5d9f9 |
| sequence_classification.md | 10.3 kB | | a4c4b5f0 |
| summarization.html | 60.4 kB | | e6d48525 |
| summarization.md | 17.7 kB | | 85cbe471 |
| text-to-speech.html | 127 kB | | 926860a6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 1ac0e7d7 |
| token_classification.md | 13.9 kB | | abab84af |
| training_vision_backbone.html | 35.9 kB | | ac76c7f7 |
| training_vision_backbone.md | 8.7 kB | | 43076508 |
| translation.html | 54.2 kB | | 091bbb49 |
| translation.md | 10.4 kB | | e9b919cd |
| video_classification.html | 89.5 kB | | cd4d3ec9 |
| video_classification.md | 20.8 kB | | f969458e |
| video_text_to_text.html | 25.2 kB | | 04e3ad47 |
| video_text_to_text.md | 6.01 kB | | 3afa650a |
| visual_document_retrieval.html | 27 kB | | f719fea3 |
| visual_document_retrieval.md | 5.68 kB | | fc81f2ab |
| visual_question_answering.html | 69.9 kB | | a5efbff2 |
| visual_question_answering.md | 14.8 kB | | 15d9a71b |
| zero_shot_image_classification.html | 29.7 kB | | d112f8d0 |
| zero_shot_image_classification.md | 5.05 kB | | d3e7354d |
| zero_shot_object_detection.html | 57.4 kB | | a618c21a |
| zero_shot_object_detection.md | 10.4 kB | | 632ed5ac |