| any_to_any.html | 27.7 kB | | 58c55ea8 |
| any_to_any.md | 4.85 kB | | 92383a97 |
| asr.html | 72.8 kB | | b183f472 |
| asr.md | 14.9 kB | | e8cb9029 |
| audio_classification.html | 66.5 kB | | 3a93c756 |
| audio_classification.md | 12.3 kB | | 78af9cc4 |
| audio_text_to_text.html | 69.9 kB | | 61065975 |
| audio_text_to_text.md | 12.2 kB | | 776e5947 |
| document_question_answering.html | 110 kB | | aa223ce0 |
| document_question_answering.md | 24.1 kB | | b481ae09 |
| idefics.html | 69.5 kB | | 3012ce9c |
| idefics.md | 18.9 kB | | e573f9f4 |
| image_captioning.html | 50.6 kB | | bbe5fb70 |
| image_captioning.md | 7.4 kB | | c452f88c |
| image_classification.html | 62.2 kB | | 0a319957 |
| image_classification.md | 10.9 kB | | 516d106b |
| image_feature_extraction.html | 31.2 kB | | cbd6459c |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 62.1 kB | | b4659066 |
| image_text_to_text.md | 16.6 kB | | 09f2f08e |
| instance_segmentation.html | 72.6 kB | | a7ab0df6 |
| instance_segmentation.md | 17.4 kB | | 14483da8 |
| keypoint_detection.html | 26.6 kB | | 62158510 |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | 8bd8195d |
| keypoint_matching.md | 4.4 kB | | 0bc4eaa5 |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | 10fa640d |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.8 kB | | 0c170cbf |
| language_modeling.md | 14 kB | | 484a0c3e |
| mask_generation.html | 81.5 kB | | 07aeb551 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.7 kB | | 92db85b0 |
| masked_language_modeling.md | 13.6 kB | | 2afa397a |
| monocular_depth_estimation.html | 30.6 kB | | c2463e05 |
| monocular_depth_estimation.md | 5.82 kB | | 9b4c5891 |
| multiple_choice.html | 52.4 kB | | cbca5758 |
| multiple_choice.md | 9.42 kB | | c0bbf53b |
| object_detection.html | 93.5 kB | | 70c157a5 |
| object_detection.md | 22.8 kB | | da3e45ce |
| prompting.html | 37.8 kB | | 2e591ca3 |
| prompting.md | 13.4 kB | | 15874f08 |
| question_answering.html | 56 kB | | 04ae08d2 |
| question_answering.md | 11.4 kB | | 96af0671 |
| semantic_segmentation.html | 116 kB | | e5db148e |
| semantic_segmentation.md | 23.7 kB | | 9dd7299a |
| sequence_classification.html | 55 kB | | 5f8f0805 |
| sequence_classification.md | 10.3 kB | | 42066e1c |
| summarization.html | 61.5 kB | | dc3774ed |
| summarization.md | 17.7 kB | | f1f8e96a |
| text-to-speech.html | 130 kB | | a93021e8 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.4 kB | | fa84b288 |
| token_classification.md | 13.9 kB | | 428d7c27 |
| training_vision_backbone.html | 36.8 kB | | 8cb6140f |
| training_vision_backbone.md | 8.7 kB | | 12cda493 |
| translation.html | 55.2 kB | | c0c9a818 |
| translation.md | 10.4 kB | | b66535a8 |
| video_classification.html | 91.4 kB | | a769fc83 |
| video_classification.md | 20.8 kB | | bd104120 |
| video_text_to_text.html | 26 kB | | cdc8cc41 |
| video_text_to_text.md | 5.91 kB | | f3a7af13 |
| visual_document_retrieval.html | 27.9 kB | | 35b9eb57 |
| visual_document_retrieval.md | 5.68 kB | | 445c8e2a |
| visual_question_answering.html | 71.5 kB | | e97e9cde |
| visual_question_answering.md | 14.8 kB | | 4557b59f |
| zero_shot_image_classification.html | 30.5 kB | | 13e0a5e6 |
| zero_shot_image_classification.md | 5.05 kB | | e6a82823 |
| zero_shot_object_detection.html | 58.6 kB | | db556800 |
| zero_shot_object_detection.md | 10.3 kB | | 5034ad18 |
