| any_to_any.html | 26.9 kB | | bb75eab1 |
| any_to_any.md | 4.85 kB | | 03d4cd8d |
| asr.html | 71.4 kB | | 77eb6fe8 |
| asr.md | 14.9 kB | | 93b9c9f3 |
| audio_classification.html | 65 kB | | 2c0a7c6c |
| audio_classification.md | 12.3 kB | | 5e550fbd |
| audio_text_to_text.html | 69.7 kB | | 05b5cc61 |
| audio_text_to_text.md | 12.7 kB | | 4cfd1894 |
| document_question_answering.html | 108 kB | | 5ce7af79 |
| document_question_answering.md | 24.1 kB | | 38d273d1 |
| image_captioning.html | 49.3 kB | | ca0e09a9 |
| image_captioning.md | 7.39 kB | | 5f0b8b26 |
| image_classification.html | 60.7 kB | | eff0895e |
| image_classification.md | 10.9 kB | | 0b19976e |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 3bde75d0 |
| image_text_to_text.md | 16.7 kB | | 9c5df3c2 |
| instance_segmentation.html | 74.1 kB | | d3d633aa |
| instance_segmentation.md | 18 kB | | 2eece908 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 07a91ca5 |
| keypoint_matching.md | 4.4 kB | | b89268b1 |
| 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 | | 9fb99dc0 |
| language_modeling.md | 14 kB | | d30e972b |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | a33b6664 |
| masked_language_modeling.md | 13.6 kB | | 56f60d11 |
| monocular_depth_estimation.html | 29.4 kB | | de117d94 |
| monocular_depth_estimation.md | 5.78 kB | | 6aa777ba |
| multiple_choice.html | 51.3 kB | | 6e7caea2 |
| multiple_choice.md | 9.41 kB | | 2d0b7d08 |
| object_detection.html | 91.9 kB | | ef2c361f |
| object_detection.md | 22.8 kB | | e04ebfdf |
| prompting.html | 37.1 kB | | fd5785fe |
| prompting.md | 13.4 kB | | c854577f |
| question_answering.html | 54.6 kB | | 75c819ab |
| question_answering.md | 11.3 kB | | 2f7c6ed7 |
| semantic_segmentation.html | 107 kB | | d0409c11 |
| semantic_segmentation.md | 21.3 kB | | a177a14d |
| sequence_classification.html | 53.8 kB | | ccb5f374 |
| sequence_classification.md | 10.3 kB | | a632b420 |
| summarization.html | 60.2 kB | | 34684847 |
| summarization.md | 17.7 kB | | f27689c3 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | b3a0266a |
| token_classification.md | 13.9 kB | | 6364ae18 |
| training_vision_backbone.html | 35.8 kB | | a71092ac |
| training_vision_backbone.md | 8.7 kB | | 394666f3 |
| translation.html | 54 kB | | ffd8397e |
| translation.md | 10.4 kB | | bd410369 |
| video_classification.html | 89.3 kB | | 6ed01d4e |
| video_classification.md | 20.8 kB | | f1821fe0 |
| video_text_to_text.html | 25.1 kB | | 53dff3c5 |
| video_text_to_text.md | 6.01 kB | | 35a873cf |
| visual_document_retrieval.html | 26.9 kB | | 1f2d26b5 |
| visual_document_retrieval.md | 5.68 kB | | d1c8a6e6 |
| visual_question_answering.html | 69.7 kB | | 619ec1d1 |
| visual_question_answering.md | 14.8 kB | | 92dee6ad |
| zero_shot_image_classification.html | 29.6 kB | | 36058ada |
| zero_shot_image_classification.md | 5.05 kB | | c06e20dc |
| zero_shot_object_detection.html | 57.3 kB | | d214cc45 |
| zero_shot_object_detection.md | 10.4 kB | | 266de073 |