| any_to_any.html | 27.5 kB | | 963dfa4d |
| any_to_any.md | 4.85 kB | | 0ccc6039 |
| asr.html | 72.5 kB | | 768e3053 |
| asr.md | 14.9 kB | | fa6fe881 |
| audio_classification.html | 66.2 kB | | e8752044 |
| audio_classification.md | 12.3 kB | | 041803dd |
| audio_text_to_text.html | 69.6 kB | | c83fb652 |
| audio_text_to_text.md | 12.2 kB | | 366d193c |
| document_question_answering.html | 109 kB | | b9fee6a1 |
| document_question_answering.md | 23.4 kB | | baedf7d7 |
| idefics.html | 69.4 kB | | 27fa22a1 |
| idefics.md | 18.5 kB | | ea899c8e |
| image_captioning.html | 50.3 kB | | 0dabe568 |
| image_captioning.md | 7.4 kB | | d1ac21b5 |
| image_classification.html | 61.9 kB | | 3303f122 |
| image_classification.md | 10.8 kB | | b80c8a7e |
| image_feature_extraction.html | 31 kB | | 71c15079 |
| image_feature_extraction.md | 4.48 kB | | d1f18593 |
| image_text_to_text.html | 51 kB | | af3c4efc |
| image_text_to_text.md | 12 kB | | 68f81323 |
| keypoint_detection.html | 26.5 kB | | 55bef4e1 |
| keypoint_detection.md | 4.4 kB | | b8776f93 |
| keypoint_matching.html | 24.4 kB | | b7af8398 |
| keypoint_matching.md | 4.03 kB | | b211c819 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | b6386472 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.6 kB | | 433b7fc6 |
| language_modeling.md | 14 kB | | 5dc66714 |
| mask_generation.html | 81.1 kB | | 92d5817a |
| mask_generation.md | 16.9 kB | | 9d8add7f |
| masked_language_modeling.html | 64.4 kB | | 12ae5f29 |
| masked_language_modeling.md | 13.6 kB | | 2810ca17 |
| monocular_depth_estimation.html | 30.5 kB | | 344792ed |
| monocular_depth_estimation.md | 5.82 kB | | 461fab59 |
| multiple_choice.html | 52.2 kB | | eacfe3cb |
| multiple_choice.md | 9.42 kB | | d118d91d |
| object_detection.html | 122 kB | | e786b15c |
| object_detection.md | 40.9 kB | | c9ad66f2 |
| prompting.html | 37.6 kB | | b60e1dbd |
| prompting.md | 13.2 kB | | ebc0248e |
| question_answering.html | 55.8 kB | | 9fd19e44 |
| question_answering.md | 11 kB | | db008273 |
| semantic_segmentation.html | 116 kB | | a7499931 |
| semantic_segmentation.md | 22.5 kB | | 566f202c |
| sequence_classification.html | 54.7 kB | | 6364d63d |
| sequence_classification.md | 10.3 kB | | e051525a |
| summarization.html | 61.3 kB | | ba440496 |
| summarization.md | 17.7 kB | | 12500801 |
| text-to-speech.html | 129 kB | | 3cf46788 |
| text-to-speech.md | 23.5 kB | | 83f7ad69 |
| token_classification.html | 74.2 kB | | 724187df |
| token_classification.md | 13.9 kB | | e422f205 |
| training_vision_backbone.html | 36.7 kB | | dc453174 |
| training_vision_backbone.md | 8.7 kB | | 14402077 |
| translation.html | 55 kB | | 2761490a |
| translation.md | 10.4 kB | | 4209e8c5 |
| video_classification.html | 91 kB | | 9e8d59e3 |
| video_classification.md | 20.8 kB | | dfa2a34f |
| video_text_to_text.html | 25.8 kB | | fc81eea7 |
| video_text_to_text.md | 5.89 kB | | e1200736 |
| visual_document_retrieval.html | 27.7 kB | | 83b13edc |
| visual_document_retrieval.md | 5.12 kB | | c44645b1 |
| visual_question_answering.html | 71.2 kB | | 42a8d9a3 |
| visual_question_answering.md | 14.6 kB | | 26df6787 |
| zero_shot_image_classification.html | 30.4 kB | | 204b498d |
| zero_shot_image_classification.md | 5.05 kB | | c7845cc2 |
| zero_shot_object_detection.html | 58.3 kB | | a42e8e14 |
| zero_shot_object_detection.md | 10.3 kB | | ba55cc0b |
