| asr.html | 72.4 kB | | 4959a181 |
| asr.md | 15 kB | | 52c95eab |
| audio_classification.html | 66.2 kB | | 95ab19cb |
| audio_classification.md | 12.5 kB | | e6463db0 |
| document_question_answering.html | 109 kB | | b9e2db4b |
| document_question_answering.md | 24.5 kB | | d16f6385 |
| idefics.html | 69.5 kB | | a5a20215 |
| idefics.md | 20.3 kB | | 5306188b |
| image_captioning.html | 50.4 kB | | ba74dd6a |
| image_captioning.md | 7.95 kB | | b49cdc55 |
| image_classification.html | 61.8 kB | | ba98c5e5 |
| image_classification.md | 11.2 kB | | 118128b7 |
| image_feature_extraction.html | 31.1 kB | | db9e8c63 |
| image_feature_extraction.md | 4.63 kB | | bfe1a48d |
| image_text_to_text.html | 48.3 kB | | 35a03dfe |
| image_text_to_text.md | 11.2 kB | | 2723ced1 |
| image_to_image.html | 28.6 kB | | 4839ba80 |
| image_to_image.md | 4.6 kB | | 8eca672d |
| keypoint_detection.html | 26.7 kB | | 584fa4cb |
| keypoint_detection.md | 5.44 kB | | 1149093c |
| keypoint_matching.html | 24.6 kB | | d5479dc9 |
| keypoint_matching.md | 4.58 kB | | 483556bb |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 7d090f94 |
| knowledge_distillation_for_image_classification.md | 7.91 kB | | 7c88674c |
| language_modeling.html | 63.7 kB | | b3b064d9 |
| language_modeling.md | 14.2 kB | | 696df906 |
| mask_generation.html | 39.6 kB | | 08f3e6b2 |
| mask_generation.md | 8.11 kB | | 22c3027d |
| masked_language_modeling.html | 64.5 kB | | 27808eb0 |
| masked_language_modeling.md | 13.9 kB | | dba32d74 |
| monocular_depth_estimation.html | 30.6 kB | | 1b5b7c06 |
| monocular_depth_estimation.md | 6.78 kB | | d4d0ac11 |
| multiple_choice.html | 52.4 kB | | e8eaa0fe |
| multiple_choice.md | 9.57 kB | | 074e3d54 |
| object_detection.html | 122 kB | | 3ffd7d6b |
| object_detection.md | 48.8 kB | | 1e76d11a |
| prompting.html | 37.7 kB | | a14593b4 |
| prompting.md | 13.6 kB | | 1531ad04 |
| question_answering.html | 58.6 kB | | 84dd9880 |
| question_answering.md | 12.4 kB | | cb08e96d |
| semantic_segmentation.html | 116 kB | | 8715e80b |
| semantic_segmentation.md | 25 kB | | f1a5b09f |
| sequence_classification.html | 54.9 kB | | b7ea07d0 |
| sequence_classification.md | 10.5 kB | | 6e86c346 |
| summarization.html | 104 kB | | 559ced54 |
| summarization.md | 18.7 kB | | 3fa17b95 |
| text-to-speech.html | 123 kB | | a3bfd353 |
| text-to-speech.md | 23.1 kB | | b91a058b |
| token_classification.html | 74.3 kB | | afb6937c |
| token_classification.md | 14.1 kB | | 534a0d48 |
| translation.html | 57.9 kB | | 22685a0e |
| translation.md | 11.5 kB | | 798b8894 |
| video_classification.html | 91.1 kB | | 231743eb |
| video_classification.md | 21.4 kB | | 6122a28b |
| video_text_to_text.html | 23.4 kB | | 448f67a6 |
| video_text_to_text.md | 5.86 kB | | 068bb508 |
| visual_document_retrieval.html | 27.8 kB | | 4ee69481 |
| visual_document_retrieval.md | 5.86 kB | | 64066389 |
| visual_question_answering.html | 75.7 kB | | bba4ae65 |
| visual_question_answering.md | 16.1 kB | | c111dcc3 |
| zero_shot_image_classification.html | 30.5 kB | | 632388ca |
| zero_shot_image_classification.md | 5.55 kB | | e1c1fd35 |
| zero_shot_object_detection.html | 58.5 kB | | 578398ca |
| zero_shot_object_detection.md | 11.9 kB | | 03c4295e |
