| any_to_any.html | 26.9 kB | | a1754efd |
| any_to_any.md | 4.85 kB | | 21d4d456 |
| asr.html | 71.4 kB | | 2b3e3aa6 |
| asr.md | 14.9 kB | | 3e30d426 |
| audio_classification.html | 65 kB | | 178529ca |
| audio_classification.md | 12.3 kB | | f10ee99d |
| audio_text_to_text.html | 69.7 kB | | dc4ad886 |
| audio_text_to_text.md | 12.7 kB | | f2abe8fe |
| document_question_answering.html | 108 kB | | 21503c5c |
| document_question_answering.md | 24.1 kB | | ec2e27de |
| image_captioning.html | 49.3 kB | | a576f7c2 |
| image_captioning.md | 7.39 kB | | b234ebb9 |
| image_classification.html | 60.7 kB | | 10b65245 |
| image_classification.md | 10.9 kB | | b67766fa |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | dd6fdd62 |
| image_text_to_text.md | 16.7 kB | | e3df7415 |
| instance_segmentation.html | 74.1 kB | | 1f6a83d8 |
| instance_segmentation.md | 18 kB | | d33f1eec |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 429fb106 |
| keypoint_matching.md | 4.4 kB | | b73cbf60 |
| 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 | | 7f60d9a7 |
| language_modeling.md | 14 kB | | 1f27aa58 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | b207aa88 |
| masked_language_modeling.md | 13.6 kB | | c6a9e5f4 |
| monocular_depth_estimation.html | 29.4 kB | | 51e802f2 |
| monocular_depth_estimation.md | 5.78 kB | | 11bd1c2f |
| multiple_choice.html | 51.3 kB | | e3f74863 |
| multiple_choice.md | 9.41 kB | | 3cb3140f |
| object_detection.html | 91.9 kB | | ecf5453f |
| object_detection.md | 22.8 kB | | 9dc3dcaa |
| prompting.html | 37.1 kB | | 85704ed4 |
| prompting.md | 13.4 kB | | e39cc793 |
| question_answering.html | 54.6 kB | | ef610f46 |
| question_answering.md | 11.3 kB | | 2f185981 |
| semantic_segmentation.html | 107 kB | | d98d9590 |
| semantic_segmentation.md | 21.3 kB | | 99635574 |
| sequence_classification.html | 53.8 kB | | e424b164 |
| sequence_classification.md | 10.3 kB | | cab690ea |
| summarization.html | 60.2 kB | | bd32825e |
| summarization.md | 17.7 kB | | d73495f7 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | b058ab5a |
| token_classification.md | 13.9 kB | | 2ca945a7 |
| training_vision_backbone.html | 35.8 kB | | 1b4cb8c4 |
| training_vision_backbone.md | 8.7 kB | | 6eddade4 |
| translation.html | 54 kB | | 00f766b5 |
| translation.md | 10.4 kB | | a9efe15a |
| video_classification.html | 89.3 kB | | 8399898b |
| video_classification.md | 20.8 kB | | ad376c70 |
| video_text_to_text.html | 25.1 kB | | e5e38285 |
| video_text_to_text.md | 6.01 kB | | 2ab3401c |
| visual_document_retrieval.html | 26.9 kB | | d5b200b9 |
| visual_document_retrieval.md | 5.68 kB | | 22edaa21 |
| visual_question_answering.html | 69.8 kB | | 311e4d7f |
| visual_question_answering.md | 14.8 kB | | 089aa54b |
| zero_shot_image_classification.html | 29.6 kB | | 42b2c7bb |
| zero_shot_image_classification.md | 5.05 kB | | 69d9d7ff |
| zero_shot_object_detection.html | 57.3 kB | | 677b538f |
| zero_shot_object_detection.md | 10.4 kB | | 811aa41f |