| any_to_any.html | 26.9 kB | | 40963ddb |
| any_to_any.md | 4.85 kB | | 311672e5 |
| asr.html | 71.4 kB | | 35e48a75 |
| asr.md | 14.9 kB | | db6caec4 |
| audio_classification.html | 65 kB | | b31ba659 |
| audio_classification.md | 12.3 kB | | 720ac455 |
| audio_text_to_text.html | 69.7 kB | | fe05fa31 |
| audio_text_to_text.md | 12.7 kB | | 78ae954a |
| document_question_answering.html | 108 kB | | 81a49ce4 |
| document_question_answering.md | 24.1 kB | | cb4799fa |
| image_captioning.html | 49.3 kB | | cb0420d9 |
| image_captioning.md | 7.39 kB | | db6e7b6e |
| image_classification.html | 60.7 kB | | f6065ece |
| image_classification.md | 10.9 kB | | 7e84c1bc |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 62.3 kB | | 6d3450c4 |
| image_text_to_text.md | 16.7 kB | | 89b99a83 |
| instance_segmentation.html | 74.1 kB | | ecc368c3 |
| instance_segmentation.md | 18 kB | | fbb511c5 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 855de2d0 |
| keypoint_matching.md | 4.4 kB | | b74317f0 |
| knowledge_distillation_for_image_classification.html | 31.6 kB | | 234bf223 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.4 kB | | dbf047b4 |
| language_modeling.md | 14 kB | | 6587e7b0 |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | dfbe8a86 |
| masked_language_modeling.md | 13.6 kB | | 111c802e |
| monocular_depth_estimation.html | 29.4 kB | | 58cf1644 |
| monocular_depth_estimation.md | 5.78 kB | | f36961f8 |
| multiple_choice.html | 51.3 kB | | 8211785d |
| multiple_choice.md | 9.41 kB | | ea4e0611 |
| object_detection.html | 91.9 kB | | ec6d7b9b |
| object_detection.md | 22.8 kB | | ff6578ab |
| prompting.html | 37.1 kB | | 21f412a2 |
| prompting.md | 13.4 kB | | 40f85994 |
| question_answering.html | 54.6 kB | | 5c29bbec |
| question_answering.md | 11.3 kB | | 27eca589 |
| semantic_segmentation.html | 106 kB | | 09be4beb |
| semantic_segmentation.md | 21.3 kB | | 96ea7429 |
| sequence_classification.html | 53.8 kB | | 9cbb8a5b |
| sequence_classification.md | 10.3 kB | | 2d32313e |
| summarization.html | 60.2 kB | | 68105c77 |
| summarization.md | 17.7 kB | | b06b6553 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 02b82b1e |
| token_classification.md | 13.9 kB | | 0f4234fd |
| training_vision_backbone.html | 35.8 kB | | be595520 |
| training_vision_backbone.md | 8.7 kB | | 480b3e15 |
| translation.html | 54 kB | | 9f160698 |
| translation.md | 10.4 kB | | b73186a9 |
| video_classification.html | 89.3 kB | | 9f987a73 |
| video_classification.md | 20.8 kB | | 0fdadd0f |
| video_text_to_text.html | 25.1 kB | | c1246378 |
| video_text_to_text.md | 6.01 kB | | fdc3db54 |
| visual_document_retrieval.html | 26.9 kB | | 825aa163 |
| visual_document_retrieval.md | 5.68 kB | | af5c511f |
| visual_question_answering.html | 69.7 kB | | 26aa53cd |
| visual_question_answering.md | 14.8 kB | | 5749ea32 |
| zero_shot_image_classification.html | 29.6 kB | | 245fe07e |
| zero_shot_image_classification.md | 5.05 kB | | 717530bc |
| zero_shot_object_detection.html | 57.3 kB | | 2acb594b |
| zero_shot_object_detection.md | 10.4 kB | | e77f2665 |
