| any_to_any.html | 26.9 kB | | 224d36cb |
| any_to_any.md | 4.85 kB | | 9f607865 |
| asr.html | 71.4 kB | | 4f9b6f8e |
| asr.md | 14.9 kB | | 84005c67 |
| audio_classification.html | 65 kB | | 65ae5b59 |
| audio_classification.md | 12.3 kB | | 21ca9da4 |
| audio_text_to_text.html | 69.7 kB | | f4fc1304 |
| audio_text_to_text.md | 12.7 kB | | f2e962d2 |
| document_question_answering.html | 108 kB | | 06381ac0 |
| document_question_answering.md | 24.1 kB | | 26d1083f |
| image_captioning.html | 49.3 kB | | 837ac30c |
| image_captioning.md | 7.39 kB | | 52c2a7ba |
| image_classification.html | 60.7 kB | | 0b3f984c |
| image_classification.md | 10.9 kB | | 6b2a57ca |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 5c14b475 |
| image_text_to_text.md | 16.7 kB | | cdbb1e1d |
| instance_segmentation.html | 74.1 kB | | 5a7f7f9a |
| instance_segmentation.md | 18 kB | | 11eb465b |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | d6996259 |
| keypoint_matching.md | 4.4 kB | | 925c642a |
| 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 | | 51e0fbd7 |
| language_modeling.md | 14 kB | | b5dfc2a1 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | d0078427 |
| masked_language_modeling.md | 13.6 kB | | 259f2199 |
| monocular_depth_estimation.html | 29.4 kB | | 8134c8d1 |
| monocular_depth_estimation.md | 5.78 kB | | ca9353d8 |
| multiple_choice.html | 51.3 kB | | f7deb0a6 |
| multiple_choice.md | 9.41 kB | | 31978ab5 |
| object_detection.html | 91.9 kB | | 4722c737 |
| object_detection.md | 22.8 kB | | b5f012d6 |
| prompting.html | 37.1 kB | | 5e29185b |
| prompting.md | 13.4 kB | | 43b8d5f6 |
| question_answering.html | 54.6 kB | | 405b0a40 |
| question_answering.md | 11.3 kB | | b161819b |
| semantic_segmentation.html | 107 kB | | f2a3e0af |
| semantic_segmentation.md | 21.3 kB | | e4137fb9 |
| sequence_classification.html | 53.8 kB | | baa5257d |
| sequence_classification.md | 10.3 kB | | c04ece8f |
| summarization.html | 60.2 kB | | ddffa249 |
| summarization.md | 17.7 kB | | a44fd2de |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 4f629921 |
| token_classification.md | 13.9 kB | | e74260b7 |
| training_vision_backbone.html | 35.8 kB | | 04f6fd3c |
| training_vision_backbone.md | 8.7 kB | | 3d1c6d99 |
| translation.html | 54 kB | | f43ccecd |
| translation.md | 10.4 kB | | f8085574 |
| video_classification.html | 89.3 kB | | fd9da6c7 |
| video_classification.md | 20.8 kB | | 99cd659b |
| video_text_to_text.html | 25.1 kB | | 21533b5f |
| video_text_to_text.md | 6.01 kB | | 34b9f1f6 |
| visual_document_retrieval.html | 26.9 kB | | 431b503c |
| visual_document_retrieval.md | 5.68 kB | | ad5fa605 |
| visual_question_answering.html | 69.7 kB | | 79e8deeb |
| visual_question_answering.md | 14.8 kB | | 2b90c7e3 |
| zero_shot_image_classification.html | 29.6 kB | | 60d82a9b |
| zero_shot_image_classification.md | 5.05 kB | | 94379360 |
| zero_shot_object_detection.html | 57.3 kB | | 9b33f353 |
| zero_shot_object_detection.md | 10.4 kB | | 5e97ba3b |