| any_to_any.html | 27.6 kB | | b540f1ea |
| any_to_any.md | 4.85 kB | | 57d6dcad |
| asr.html | 72.8 kB | | 845c6563 |
| asr.md | 14.9 kB | | d940e0f9 |
| audio_classification.html | 66.5 kB | | bcc3c039 |
| audio_classification.md | 12.3 kB | | 93a0011d |
| audio_text_to_text.html | 69.9 kB | | f22d68fe |
| audio_text_to_text.md | 12.2 kB | | c5fe1d60 |
| document_question_answering.html | 110 kB | | dc396a3d |
| document_question_answering.md | 24.1 kB | | 0a858f81 |
| idefics.html | 69.5 kB | | b3fccaee |
| idefics.md | 18.9 kB | | 49be9053 |
| image_captioning.html | 50.6 kB | | 14c8252e |
| image_captioning.md | 7.4 kB | | c645c493 |
| image_classification.html | 62.2 kB | | 49633bc5 |
| image_classification.md | 10.9 kB | | fee0c40e |
| image_feature_extraction.html | 31.2 kB | | b74d6418 |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 62.1 kB | | a122f22e |
| image_text_to_text.md | 16.6 kB | | 523fd65f |
| instance_segmentation.html | 72.6 kB | | 9c93d5df |
| instance_segmentation.md | 17.4 kB | | bf0afd5a |
| keypoint_detection.html | 26.6 kB | | e5a856d5 |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | 68c57817 |
| keypoint_matching.md | 4.4 kB | | e26ece0d |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | 30cd3700 |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.8 kB | | 93d2560c |
| language_modeling.md | 14 kB | | ba159909 |
| mask_generation.html | 81.5 kB | | 59874487 |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.7 kB | | 9aca191a |
| masked_language_modeling.md | 13.6 kB | | b2f1e5fc |
| monocular_depth_estimation.html | 30.6 kB | | 8b9f4e24 |
| monocular_depth_estimation.md | 5.82 kB | | 218c7e49 |
| multiple_choice.html | 52.4 kB | | f81dee8c |
| multiple_choice.md | 9.42 kB | | 40178f9c |
| object_detection.html | 93.5 kB | | df4e1cbd |
| object_detection.md | 22.8 kB | | 89f7b7d3 |
| prompting.html | 37.8 kB | | cffd00d8 |
| prompting.md | 13.4 kB | | bf8bf438 |
| question_answering.html | 56 kB | | d2732b99 |
| question_answering.md | 11.4 kB | | 9fc91d2a |
| semantic_segmentation.html | 116 kB | | 1c39cc4f |
| semantic_segmentation.md | 23.7 kB | | 457aed1a |
| sequence_classification.html | 55 kB | | 68ebded2 |
| sequence_classification.md | 10.3 kB | | 7fd0f812 |
| summarization.html | 61.5 kB | | 744975c0 |
| summarization.md | 17.7 kB | | ecafded8 |
| text-to-speech.html | 130 kB | | 01aa2350 |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.4 kB | | bed98a9e |
| token_classification.md | 13.9 kB | | 7b6eaec7 |
| training_vision_backbone.html | 36.8 kB | | 7e447068 |
| training_vision_backbone.md | 8.7 kB | | bb3ac352 |
| translation.html | 55.2 kB | | 239215e5 |
| translation.md | 10.4 kB | | 029614f5 |
| video_classification.html | 91.4 kB | | 6e56f8f2 |
| video_classification.md | 20.8 kB | | 0db6c234 |
| video_text_to_text.html | 26 kB | | 122bcf41 |
| video_text_to_text.md | 5.91 kB | | fa81dee3 |
| visual_document_retrieval.html | 27.9 kB | | 00125d01 |
| visual_document_retrieval.md | 5.68 kB | | 50bc7f78 |
| visual_question_answering.html | 71.5 kB | | 176a4bf1 |
| visual_question_answering.md | 14.8 kB | | b3407c12 |
| zero_shot_image_classification.html | 30.5 kB | | 2caf0ed0 |
| zero_shot_image_classification.md | 5.05 kB | | 082d12d3 |
| zero_shot_object_detection.html | 58.6 kB | | 314c2952 |
| zero_shot_object_detection.md | 10.3 kB | | 45621004 |
