| any_to_any.html | 26.9 kB | | 8b029609 |
| any_to_any.md | 4.85 kB | | 19aad402 |
| asr.html | 71.4 kB | | 326c673b |
| asr.md | 14.9 kB | | 0b7f86a7 |
| audio_classification.html | 65 kB | | 7614a955 |
| audio_classification.md | 12.3 kB | | d18ab92f |
| audio_text_to_text.html | 69.7 kB | | d362ef91 |
| audio_text_to_text.md | 12.7 kB | | b4d60f7e |
| document_question_answering.html | 108 kB | | b09e8344 |
| document_question_answering.md | 24.1 kB | | a5b5af7b |
| image_captioning.html | 49.3 kB | | 51a47275 |
| image_captioning.md | 7.39 kB | | 43e96540 |
| image_classification.html | 60.7 kB | | 33ba52df |
| image_classification.md | 10.9 kB | | 4ecbfb6c |
| image_feature_extraction.html | 30.4 kB | | 7c59c65a |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 63.9 kB | | 7563fc44 |
| image_text_to_text.md | 17.1 kB | | 06beb0a5 |
| instance_segmentation.html | 74.1 kB | | fd05cc35 |
| instance_segmentation.md | 18 kB | | 45b3a418 |
| keypoint_detection.html | 25.9 kB | | c3557fc3 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.6 kB | | 97c8fd72 |
| keypoint_matching.md | 4.4 kB | | b1310b0a |
| 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 | | c224923d |
| language_modeling.md | 14 kB | | 6aec7b5c |
| mask_generation.html | 79.9 kB | | 37028b5e |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.3 kB | | 129e92b3 |
| masked_language_modeling.md | 13.6 kB | | 9c4ddc6f |
| monocular_depth_estimation.html | 29.4 kB | | 29871cb8 |
| monocular_depth_estimation.md | 5.78 kB | | 48913f38 |
| multiple_choice.html | 51.3 kB | | 2041344f |
| multiple_choice.md | 9.41 kB | | e19ddf61 |
| object_detection.html | 91.9 kB | | 5b390c8a |
| object_detection.md | 22.8 kB | | 263c6239 |
| prompting.html | 37.1 kB | | 38f59e4f |
| prompting.md | 13.4 kB | | 1c625f68 |
| question_answering.html | 54.6 kB | | 528f7a91 |
| question_answering.md | 11.3 kB | | ef52cbcc |
| semantic_segmentation.html | 107 kB | | d11734bb |
| semantic_segmentation.md | 21.3 kB | | 474cf823 |
| sequence_classification.html | 53.8 kB | | 0f266ba9 |
| sequence_classification.md | 10.3 kB | | f06c55f9 |
| summarization.html | 60.2 kB | | 58d75651 |
| summarization.md | 17.7 kB | | a792250d |
| text-to-speech.html | 127 kB | | 1e73ce77 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73 kB | | d3e278c2 |
| token_classification.md | 13.9 kB | | 01088a26 |
| training_vision_backbone.html | 35.8 kB | | f7faa4a8 |
| training_vision_backbone.md | 8.7 kB | | 160805e7 |
| translation.html | 54 kB | | c76589a3 |
| translation.md | 10.4 kB | | 45abeab6 |
| video_classification.html | 89.3 kB | | 750bae94 |
| video_classification.md | 20.8 kB | | b240548a |
| video_text_to_text.html | 25.1 kB | | fc02c356 |
| video_text_to_text.md | 6.01 kB | | 98fe00a8 |
| visual_document_retrieval.html | 26.9 kB | | 771fbbc2 |
| visual_document_retrieval.md | 5.68 kB | | b1ca2ef7 |
| visual_question_answering.html | 69.7 kB | | 474a7035 |
| visual_question_answering.md | 14.8 kB | | c880b1d5 |
| zero_shot_image_classification.html | 29.6 kB | | 0c661c91 |
| zero_shot_image_classification.md | 5.05 kB | | aec2e9c8 |
| zero_shot_object_detection.html | 57.3 kB | | 95156b4b |
| zero_shot_object_detection.md | 10.4 kB | | 3d5bc2c2 |