| any_to_any.html | 26.9 kB | | bf1a0e59 |
| any_to_any.md | 4.85 kB | | 255ef150 |
| asr.html | 71.4 kB | | 30e6a1da |
| asr.md | 14.9 kB | | f04ee7d8 |
| audio_classification.html | 65 kB | | 556725e1 |
| audio_classification.md | 12.3 kB | | 8b899eae |
| audio_text_to_text.html | 69.7 kB | | ce6f254f |
| audio_text_to_text.md | 12.7 kB | | f4a6c04c |
| document_question_answering.html | 108 kB | | f6eb93d4 |
| document_question_answering.md | 24.1 kB | | 828bc789 |
| image_captioning.html | 49.3 kB | | e8b8d509 |
| image_captioning.md | 7.39 kB | | 592946f6 |
| image_classification.html | 60.7 kB | | cfe4196a |
| image_classification.md | 10.9 kB | | 25e18892 |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | b6b20095 |
| image_text_to_text.md | 17.1 kB | | ac3a017c |
| instance_segmentation.html | 74.1 kB | | 9292cefb |
| instance_segmentation.md | 18 kB | | a8d697ff |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 392be523 |
| keypoint_matching.md | 4.4 kB | | 17c0fc6b |
| 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 | | 863c9ba9 |
| language_modeling.md | 14 kB | | 52cfd8af |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 78480aaf |
| masked_language_modeling.md | 13.6 kB | | 0d5bf1b8 |
| monocular_depth_estimation.html | 29.4 kB | | d5d2e9d2 |
| monocular_depth_estimation.md | 5.78 kB | | be5c42b6 |
| multiple_choice.html | 51.3 kB | | ed0cadf5 |
| multiple_choice.md | 9.41 kB | | d386bbb1 |
| object_detection.html | 91.9 kB | | 9df1a3a1 |
| object_detection.md | 22.8 kB | | de83a9c1 |
| prompting.html | 37.1 kB | | 69a7c1cd |
| prompting.md | 13.4 kB | | 2967cbc3 |
| question_answering.html | 54.6 kB | | a2e5f824 |
| question_answering.md | 11.3 kB | | 7833e4b9 |
| semantic_segmentation.html | 107 kB | | 2a762174 |
| semantic_segmentation.md | 21.3 kB | | bfff2979 |
| sequence_classification.html | 53.8 kB | | af03825a |
| sequence_classification.md | 10.3 kB | | 0327c1dd |
| summarization.html | 60.2 kB | | c01f58f7 |
| summarization.md | 17.7 kB | | a49d8f09 |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | 2fcd4d24 |
| token_classification.md | 13.9 kB | | b3ae2ffc |
| training_vision_backbone.html | 35.8 kB | | 5ed14cdc |
| training_vision_backbone.md | 8.7 kB | | f143dff8 |
| translation.html | 54 kB | | bab2b980 |
| translation.md | 10.4 kB | | 5d8b89f6 |
| video_classification.html | 89.3 kB | | 2bb6d4b1 |
| video_classification.md | 20.8 kB | | 543be43e |
| video_text_to_text.html | 25.1 kB | | 0ff39e49 |
| video_text_to_text.md | 6.01 kB | | 6b0f5e72 |
| visual_document_retrieval.html | 26.9 kB | | 479ac6c6 |
| visual_document_retrieval.md | 5.68 kB | | e24efbf4 |
| visual_question_answering.html | 69.7 kB | | 027c4526 |
| visual_question_answering.md | 14.8 kB | | 9e848d7a |
| zero_shot_image_classification.html | 29.6 kB | | 97d36bfc |
| zero_shot_image_classification.md | 5.05 kB | | 6e755ff8 |
| zero_shot_object_detection.html | 57.3 kB | | f02df84e |
| zero_shot_object_detection.md | 10.4 kB | | 42eb15d2 |