| any_to_any.html | 27.6 kB | | 6766df41 |
| any_to_any.md | 4.85 kB | | 8fb2b47f |
| asr.html | 72.8 kB | | ac1716fd |
| asr.md | 14.9 kB | | 84c260a8 |
| audio_classification.html | 66.5 kB | | a788f7e4 |
| audio_classification.md | 12.3 kB | | c78aaf34 |
| audio_text_to_text.html | 69.9 kB | | 474acbf3 |
| audio_text_to_text.md | 12.2 kB | | 6a6bfa3d |
| document_question_answering.html | 110 kB | | 0dabb4f1 |
| document_question_answering.md | 24.1 kB | | 90f3d29f |
| idefics.html | 69.5 kB | | 5d16677b |
| idefics.md | 18.9 kB | | f145da76 |
| image_captioning.html | 50.6 kB | | 0962b803 |
| image_captioning.md | 7.4 kB | | b37cffdb |
| image_classification.html | 62.2 kB | | 99a7cbca |
| image_classification.md | 10.9 kB | | 12294d26 |
| image_feature_extraction.html | 31.2 kB | | 351dd0d6 |
| image_feature_extraction.md | 4.5 kB | | 17144538 |
| image_text_to_text.html | 62.1 kB | | b05b79c5 |
| image_text_to_text.md | 16.6 kB | | d0515f4a |
| keypoint_detection.html | 26.6 kB | | d8bbeaab |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | 6c08ae93 |
| keypoint_matching.md | 4.4 kB | | d44c6ffa |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | 69a9e758 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.8 kB | | b4d45183 |
| language_modeling.md | 14 kB | | 60572a39 |
| mask_generation.html | 81.5 kB | | 775ce269 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.7 kB | | 83f44fe9 |
| masked_language_modeling.md | 13.6 kB | | 02c039f0 |
| monocular_depth_estimation.html | 30.6 kB | | 1eaf71fe |
| monocular_depth_estimation.md | 5.82 kB | | 22369051 |
| multiple_choice.html | 52.4 kB | | b9a0e541 |
| multiple_choice.md | 9.42 kB | | 40e8fab5 |
| object_detection.html | 123 kB | | 24118726 |
| object_detection.md | 41 kB | | 9b9261c3 |
| prompting.html | 37.8 kB | | 8d1320c5 |
| prompting.md | 13.4 kB | | fa735149 |
| question_answering.html | 56 kB | | abfe38ad |
| question_answering.md | 11.4 kB | | d6921edc |
| semantic_segmentation.html | 116 kB | | ef0952d8 |
| semantic_segmentation.md | 23.7 kB | | a7bd6a10 |
| sequence_classification.html | 55 kB | | 97a6e927 |
| sequence_classification.md | 10.3 kB | | 38d9a3a0 |
| summarization.html | 61.5 kB | | 5b1d89f3 |
| summarization.md | 17.7 kB | | 5d3f7cf1 |
| text-to-speech.html | 130 kB | | 870bc971 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.4 kB | | 3d06843f |
| token_classification.md | 13.9 kB | | e2015d03 |
| training_vision_backbone.html | 36.8 kB | | e42c230d |
| training_vision_backbone.md | 8.7 kB | | 9e035e6f |
| translation.html | 55.2 kB | | 4566f687 |
| translation.md | 10.4 kB | | bd1dce89 |
| video_classification.html | 91.4 kB | | 081f36e2 |
| video_classification.md | 20.8 kB | | ea8df44d |
| video_text_to_text.html | 26 kB | | e11b80b8 |
| video_text_to_text.md | 5.9 kB | | 448550dc |
| visual_document_retrieval.html | 27.9 kB | | 3057e8de |
| visual_document_retrieval.md | 5.68 kB | | 507845f6 |
| visual_question_answering.html | 71.5 kB | | 64f28f08 |
| visual_question_answering.md | 14.8 kB | | 0dc4626e |
| zero_shot_image_classification.html | 30.5 kB | | e5675d0e |
| zero_shot_image_classification.md | 5.05 kB | | 122b612c |
| zero_shot_object_detection.html | 58.6 kB | | 68e1aadc |
| zero_shot_object_detection.md | 10.3 kB | | b048bbb4 |
