| any_to_any.html | 27.5 kB | | 8dce2c4f |
| any_to_any.md | 4.85 kB | | 2483d8d1 |
| asr.html | 72.5 kB | | 8c6fcfb4 |
| asr.md | 14.9 kB | | 28ea2745 |
| audio_classification.html | 66.2 kB | | bf8a7ce7 |
| audio_classification.md | 12.3 kB | | 38b32485 |
| audio_text_to_text.html | 69.6 kB | | da1466b2 |
| audio_text_to_text.md | 12.2 kB | | a378d3d4 |
| document_question_answering.html | 109 kB | | 1de7dc2d |
| document_question_answering.md | 23.4 kB | | 1f5858f6 |
| idefics.html | 69.4 kB | | a2a76421 |
| idefics.md | 18.5 kB | | 417a07d2 |
| image_captioning.html | 50.3 kB | | 19b3a897 |
| image_captioning.md | 7.4 kB | | 68fd49bc |
| image_classification.html | 61.9 kB | | 6fc78197 |
| image_classification.md | 10.8 kB | | 26fcb34f |
| image_feature_extraction.html | 31 kB | | 176f2d44 |
| image_feature_extraction.md | 4.48 kB | | d1f18593 |
| image_text_to_text.html | 61.9 kB | | fb2d57af |
| image_text_to_text.md | 16.5 kB | | ee171bfb |
| keypoint_detection.html | 26.5 kB | | 0b269a5c |
| keypoint_detection.md | 4.4 kB | | b8776f93 |
| keypoint_matching.html | 24.4 kB | | 73a5f5c6 |
| keypoint_matching.md | 4.03 kB | | 4901b2a8 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | a42bfe26 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.6 kB | | 17b10ca4 |
| language_modeling.md | 14 kB | | dd890fec |
| mask_generation.html | 81.1 kB | | 6ac7617d |
| mask_generation.md | 16.9 kB | | 9d8add7f |
| masked_language_modeling.html | 64.4 kB | | 4a706160 |
| masked_language_modeling.md | 13.6 kB | | ccb425f3 |
| monocular_depth_estimation.html | 30.5 kB | | 53196a3f |
| monocular_depth_estimation.md | 5.82 kB | | 5dd215ad |
| multiple_choice.html | 52.2 kB | | a2873caa |
| multiple_choice.md | 9.42 kB | | bc64f9f5 |
| object_detection.html | 122 kB | | a193c9fc |
| object_detection.md | 40.9 kB | | 6bc30ee5 |
| prompting.html | 37.7 kB | | 26f148a8 |
| prompting.md | 13.4 kB | | 0dcf613f |
| question_answering.html | 55.8 kB | | 0f3509fa |
| question_answering.md | 11 kB | | 2fbdb657 |
| semantic_segmentation.html | 116 kB | | f8c83456 |
| semantic_segmentation.md | 22.5 kB | | 58b0d0be |
| sequence_classification.html | 54.7 kB | | 5e03d676 |
| sequence_classification.md | 10.3 kB | | 199b8b83 |
| summarization.html | 61.3 kB | | 67c359bb |
| summarization.md | 17.7 kB | | abcae132 |
| text-to-speech.html | 129 kB | | 5e6f88ce |
| text-to-speech.md | 23.5 kB | | 83f7ad69 |
| token_classification.html | 74.2 kB | | 6fc88da6 |
| token_classification.md | 13.9 kB | | a3a97e66 |
| training_vision_backbone.html | 36.7 kB | | 1500cb46 |
| training_vision_backbone.md | 8.7 kB | | 959f66d7 |
| translation.html | 55 kB | | b2103d03 |
| translation.md | 10.4 kB | | 3cb8dd21 |
| video_classification.html | 91 kB | | b166b387 |
| video_classification.md | 20.8 kB | | 2e22b827 |
| video_text_to_text.html | 25.8 kB | | 0a759c6d |
| video_text_to_text.md | 5.89 kB | | e7c44b37 |
| visual_document_retrieval.html | 27.7 kB | | d0a3f3a2 |
| visual_document_retrieval.md | 5.12 kB | | 861a7b38 |
| visual_question_answering.html | 71.2 kB | | 5557b483 |
| visual_question_answering.md | 14.6 kB | | 4524ed93 |
| zero_shot_image_classification.html | 30.4 kB | | f7adaf98 |
| zero_shot_image_classification.md | 5.05 kB | | 6aeed0ac |
| zero_shot_object_detection.html | 58.3 kB | | d05ce3ce |
| zero_shot_object_detection.md | 10.3 kB | | 1d2368d6 |
