| any_to_any.html | 27 kB | | 79805e71 |
| any_to_any.md | 4.85 kB | | 5120fb50 |
| asr.html | 71.5 kB | | d9a2cf8d |
| asr.md | 14.9 kB | | 3943370e |
| audio_classification.html | 65.1 kB | | f4269144 |
| audio_classification.md | 12.3 kB | | f34d535e |
| audio_text_to_text.html | 69.9 kB | | 959d3bf7 |
| audio_text_to_text.md | 12.7 kB | | e2243531 |
| document_question_answering.html | 108 kB | | 3cebe02f |
| document_question_answering.md | 24.1 kB | | b0148beb |
| image_captioning.html | 49.5 kB | | aaec6892 |
| image_captioning.md | 7.39 kB | | 71f6a6d8 |
| image_classification.html | 60.9 kB | | 1b1733ea |
| image_classification.md | 10.9 kB | | 6638ca9c |
| image_feature_extraction.html | 30.5 kB | | d7597116 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.1 kB | | 508a4347 |
| image_text_to_text.md | 17 kB | | f456170c |
| instance_segmentation.html | 74.3 kB | | 7a1a62be |
| instance_segmentation.md | 18 kB | | 3c6a9cd6 |
| keypoint_detection.html | 26 kB | | 69d9360e |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | baa2cc41 |
| keypoint_matching.md | 4.4 kB | | d715854d |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | fdde2a8b |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 0d7d5f23 |
| language_modeling.md | 14 kB | | 268116f6 |
| mask_generation.html | 80 kB | | 88e3c7a7 |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | d234fa3f |
| masked_language_modeling.md | 13.6 kB | | 112f8d66 |
| monocular_depth_estimation.html | 29.5 kB | | bc3efb1f |
| monocular_depth_estimation.md | 5.78 kB | | da3346f3 |
| multiple_choice.html | 51.4 kB | | 657c9a84 |
| multiple_choice.md | 9.41 kB | | cc291bce |
| object_detection.html | 92 kB | | 3495f835 |
| object_detection.md | 22.8 kB | | cc3b89f5 |
| prompting.html | 45.6 kB | | f68ee1f7 |
| prompting.md | 13.4 kB | | 951f9184 |
| question_answering.html | 54.8 kB | | 86ed185c |
| question_answering.md | 11.3 kB | | 5bb24e22 |
| semantic_segmentation.html | 107 kB | | 4a4fca81 |
| semantic_segmentation.md | 21.3 kB | | 62fc86b1 |
| sequence_classification.html | 53.9 kB | | ea841ced |
| sequence_classification.md | 10.3 kB | | f4e3e86f |
| summarization.html | 60.4 kB | | be1c1e12 |
| summarization.md | 17.7 kB | | 75167ecb |
| text-to-speech.html | 127 kB | | 6db99785 |
| text-to-speech.md | 23.6 kB | | b755646f |
| token_classification.html | 73.1 kB | | 91ec1c9d |
| token_classification.md | 13.9 kB | | 3c68c319 |
| training_vision_backbone.html | 35.9 kB | | 05e5bf42 |
| training_vision_backbone.md | 8.7 kB | | 3a9a13c6 |
| translation.html | 54.2 kB | | 808e1d6a |
| translation.md | 10.4 kB | | 2281fa24 |
| video_classification.html | 89.2 kB | | 4a0ecef8 |
| video_classification.md | 20.6 kB | | a97af000 |
| video_text_to_text.html | 25.2 kB | | ed0f72a7 |
| video_text_to_text.md | 6.01 kB | | ed8dfdac |
| visual_document_retrieval.html | 27 kB | | 802aa64d |
| visual_document_retrieval.md | 5.68 kB | | 69972edb |
| visual_question_answering.html | 69.6 kB | | 2a89fab1 |
| visual_question_answering.md | 14.6 kB | | 8730def0 |
| zero_shot_image_classification.html | 29.7 kB | | 05f6f9e1 |
| zero_shot_image_classification.md | 5.05 kB | | 52dab4b5 |
| zero_shot_object_detection.html | 57.4 kB | | 28cc2f26 |
| zero_shot_object_detection.md | 10.4 kB | | 4da741ac |