| any_to_any.html | 26.9 kB | | 724651f5 |
| any_to_any.md | 4.85 kB | | 3d1e0029 |
| asr.html | 71.4 kB | | f5840fbf |
| asr.md | 14.9 kB | | 12ab39f9 |
| audio_classification.html | 65 kB | | c5d751b1 |
| audio_classification.md | 12.3 kB | | 7bb6734b |
| audio_text_to_text.html | 69.7 kB | | 6e2cea87 |
| audio_text_to_text.md | 12.7 kB | | d0b9b7ec |
| document_question_answering.html | 108 kB | | 888c3c05 |
| document_question_answering.md | 24.1 kB | | c3329216 |
| image_captioning.html | 49.3 kB | | 72fc3d82 |
| image_captioning.md | 7.39 kB | | ddb543a2 |
| image_classification.html | 60.7 kB | | 2528225b |
| image_classification.md | 10.9 kB | | c12de529 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 1f4dcd71 |
| image_text_to_text.md | 16.7 kB | | d17622fd |
| instance_segmentation.html | 74.1 kB | | cf15d736 |
| instance_segmentation.md | 18 kB | | b15f1fa9 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 06b24fc3 |
| keypoint_matching.md | 4.4 kB | | 4c93494c |
| 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 | | 04712df7 |
| language_modeling.md | 14 kB | | 9a846d64 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 1d4af2e3 |
| masked_language_modeling.md | 13.6 kB | | 08dce325 |
| monocular_depth_estimation.html | 29.4 kB | | 86c34787 |
| monocular_depth_estimation.md | 5.78 kB | | 0ccc18d2 |
| multiple_choice.html | 51.3 kB | | 01022c94 |
| multiple_choice.md | 9.41 kB | | 234ad7ca |
| object_detection.html | 91.9 kB | | e7c435ea |
| object_detection.md | 22.8 kB | | 8a6c474d |
| prompting.html | 37.1 kB | | 7f897e05 |
| prompting.md | 13.4 kB | | e1c89f92 |
| question_answering.html | 54.6 kB | | 04b1ffb4 |
| question_answering.md | 11.3 kB | | eb87103c |
| semantic_segmentation.html | 107 kB | | 7263fe1b |
| semantic_segmentation.md | 21.3 kB | | b8d024c8 |
| sequence_classification.html | 53.7 kB | | 24f0914a |
| sequence_classification.md | 10.3 kB | | 9fc1b4e9 |
| summarization.html | 60.2 kB | | 3ea5de43 |
| summarization.md | 17.7 kB | | 0a770c8b |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 2ecc798e |
| token_classification.md | 13.9 kB | | 26771a8b |
| training_vision_backbone.html | 35.8 kB | | 3cee5f5a |
| training_vision_backbone.md | 8.7 kB | | 7a806e89 |
| translation.html | 54 kB | | c2ecbf0b |
| translation.md | 10.4 kB | | f2f8e71f |
| video_classification.html | 89.3 kB | | 45ff2e1b |
| video_classification.md | 20.8 kB | | 8df887ea |
| video_text_to_text.html | 25.1 kB | | e0e9d6f4 |
| video_text_to_text.md | 6.01 kB | | d986b4bb |
| visual_document_retrieval.html | 26.9 kB | | 911ad1fd |
| visual_document_retrieval.md | 5.68 kB | | b3f61174 |
| visual_question_answering.html | 69.7 kB | | ebad0693 |
| visual_question_answering.md | 14.8 kB | | 7bbc2744 |
| zero_shot_image_classification.html | 29.6 kB | | d95b108d |
| zero_shot_image_classification.md | 5.05 kB | | bdaf96c0 |
| zero_shot_object_detection.html | 57.3 kB | | d5eccddc |
| zero_shot_object_detection.md | 10.4 kB | | e35481da |