| any_to_any.html | 26.9 kB | | fc356f60 |
| any_to_any.md | 4.85 kB | | 9f2c6547 |
| asr.html | 71.4 kB | | b4cc30fb |
| asr.md | 14.9 kB | | 6e9c2809 |
| audio_classification.html | 65 kB | | 92003a82 |
| audio_classification.md | 12.3 kB | | c3531fa6 |
| audio_text_to_text.html | 69.7 kB | | 06164195 |
| audio_text_to_text.md | 12.7 kB | | 8603f72e |
| document_question_answering.html | 108 kB | | 564a89c4 |
| document_question_answering.md | 24.1 kB | | 47d23353 |
| image_captioning.html | 49.3 kB | | 691f82f1 |
| image_captioning.md | 7.39 kB | | 74a8deb2 |
| image_classification.html | 60.7 kB | | 7559c3b3 |
| image_classification.md | 10.9 kB | | 066e29dc |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | cd30627b |
| image_text_to_text.md | 16.7 kB | | db33fa19 |
| instance_segmentation.html | 74.1 kB | | e2f75da5 |
| instance_segmentation.md | 18 kB | | fcdbc93c |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 2d02aa81 |
| keypoint_matching.md | 4.4 kB | | 24a4aceb |
| 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 | | 1afcb25b |
| language_modeling.md | 14 kB | | edb938ce |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | b86141e0 |
| masked_language_modeling.md | 13.6 kB | | 20404aec |
| monocular_depth_estimation.html | 29.4 kB | | b0e643b5 |
| monocular_depth_estimation.md | 5.78 kB | | 7a54d101 |
| multiple_choice.html | 51.3 kB | | fe7d164b |
| multiple_choice.md | 9.41 kB | | dcab526c |
| object_detection.html | 91.9 kB | | 4cd3d815 |
| object_detection.md | 22.8 kB | | 63a80baa |
| prompting.html | 37.1 kB | | 466338a0 |
| prompting.md | 13.4 kB | | 9301eaaa |
| question_answering.html | 54.6 kB | | e165a63a |
| question_answering.md | 11.3 kB | | 099459a9 |
| semantic_segmentation.html | 107 kB | | 199e7ac5 |
| semantic_segmentation.md | 21.3 kB | | 19ad6adc |
| sequence_classification.html | 53.8 kB | | a0cf74bb |
| sequence_classification.md | 10.3 kB | | b0ccff48 |
| summarization.html | 60.2 kB | | 54b5e116 |
| summarization.md | 17.7 kB | | f3a5ba59 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 23655d6c |
| token_classification.md | 13.9 kB | | 1cf1649e |
| training_vision_backbone.html | 35.8 kB | | 5821866a |
| training_vision_backbone.md | 8.7 kB | | 58621981 |
| translation.html | 54 kB | | daee0ff8 |
| translation.md | 10.4 kB | | aa61d77a |
| video_classification.html | 89.3 kB | | f125ba26 |
| video_classification.md | 20.8 kB | | 0e26cf08 |
| video_text_to_text.html | 25.1 kB | | c8096101 |
| video_text_to_text.md | 6.01 kB | | a07e122c |
| visual_document_retrieval.html | 26.9 kB | | 94743b52 |
| visual_document_retrieval.md | 5.68 kB | | 40bbd489 |
| visual_question_answering.html | 69.8 kB | | 06074ed0 |
| visual_question_answering.md | 14.8 kB | | 9cb21b0c |
| zero_shot_image_classification.html | 29.6 kB | | b5dc61f0 |
| zero_shot_image_classification.md | 5.05 kB | | e2ab36d1 |
| zero_shot_object_detection.html | 57.3 kB | | 92042369 |
| zero_shot_object_detection.md | 10.4 kB | | 838534f6 |