| any_to_any.html | 27 kB | | 3c867e24 |
| any_to_any.md | 4.85 kB | | 54ae61dc |
| asr.html | 71.5 kB | | 48c9f330 |
| asr.md | 14.9 kB | | b96169ac |
| audio_classification.html | 65.2 kB | | a6b6efdc |
| audio_classification.md | 12.3 kB | | 671b0934 |
| audio_text_to_text.html | 69.9 kB | | 213144a6 |
| audio_text_to_text.md | 12.7 kB | | 2f05b4eb |
| document_question_answering.html | 108 kB | | 695f166a |
| document_question_answering.md | 24.1 kB | | 9e3060b7 |
| image_captioning.html | 49.5 kB | | b59ac449 |
| image_captioning.md | 7.39 kB | | bbb22376 |
| image_classification.html | 60.9 kB | | a9adc99d |
| image_classification.md | 10.9 kB | | 73ff0090 |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | 7b3472ed |
| image_text_to_text.md | 17.1 kB | | 7264a818 |
| instance_segmentation.html | 74.3 kB | | a1355c91 |
| instance_segmentation.md | 18 kB | | 93d373d7 |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | a2abeab1 |
| keypoint_matching.md | 4.4 kB | | 0c1d26b2 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | fdde2a8b |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 8f890002 |
| language_modeling.md | 14 kB | | 3d758128 |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 6b95d2e0 |
| masked_language_modeling.md | 13.6 kB | | 790cf2a9 |
| monocular_depth_estimation.html | 29.5 kB | | 5ed9298f |
| monocular_depth_estimation.md | 5.78 kB | | 3f5e8149 |
| multiple_choice.html | 51.4 kB | | 50321eb6 |
| multiple_choice.md | 9.41 kB | | 33f9b629 |
| object_detection.html | 92 kB | | 4f934466 |
| object_detection.md | 22.8 kB | | 8eeecd13 |
| prompting.html | 45.6 kB | | 9b69484e |
| prompting.md | 13.4 kB | | ab80414a |
| question_answering.html | 54.8 kB | | e868083e |
| question_answering.md | 11.3 kB | | 71eaa382 |
| semantic_segmentation.html | 107 kB | | a9124012 |
| semantic_segmentation.md | 21.3 kB | | a17bd237 |
| sequence_classification.html | 53.9 kB | | 2914d370 |
| sequence_classification.md | 10.3 kB | | 5962fdae |
| summarization.html | 60.4 kB | | f1ce1c66 |
| summarization.md | 17.7 kB | | dc8dc7b9 |
| text-to-speech.html | 127 kB | | 15560dcd |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 3f1e189a |
| token_classification.md | 13.9 kB | | 73724c89 |
| training_vision_backbone.html | 35.9 kB | | d5764367 |
| training_vision_backbone.md | 8.7 kB | | e8c6ea61 |
| translation.html | 54.2 kB | | cc98447f |
| translation.md | 10.4 kB | | 0b77f448 |
| video_classification.html | 89.5 kB | | 80a3055c |
| video_classification.md | 20.8 kB | | 5734cb03 |
| video_text_to_text.html | 25.2 kB | | ece5b1cd |
| video_text_to_text.md | 6.01 kB | | 8bcbefc2 |
| visual_document_retrieval.html | 27 kB | | 080b9ab7 |
| visual_document_retrieval.md | 5.68 kB | | 2aabf405 |
| visual_question_answering.html | 69.9 kB | | bd5c0187 |
| visual_question_answering.md | 14.8 kB | | 20451dbc |
| zero_shot_image_classification.html | 29.7 kB | | d5aa611a |
| zero_shot_image_classification.md | 5.05 kB | | 30d1dad7 |
| zero_shot_object_detection.html | 57.4 kB | | 6997bb43 |
| zero_shot_object_detection.md | 10.4 kB | | 4a362d41 |