| any_to_any.html | 27 kB | | 9ef0c97e |
| any_to_any.md | 4.85 kB | | c794bf35 |
| asr.html | 71.5 kB | | 5664a176 |
| asr.md | 14.9 kB | | 15af1729 |
| audio_classification.html | 65.2 kB | | 6e28d287 |
| audio_classification.md | 12.3 kB | | 63782402 |
| audio_text_to_text.html | 69.9 kB | | 6a7e04ee |
| audio_text_to_text.md | 12.7 kB | | e8a8d951 |
| document_question_answering.html | 108 kB | | ee20d27e |
| document_question_answering.md | 24.1 kB | | 30876467 |
| image_captioning.html | 49.5 kB | | e6fe07f2 |
| image_captioning.md | 7.39 kB | | c2aff91f |
| image_classification.html | 60.9 kB | | 1858dfcd |
| image_classification.md | 10.9 kB | | 5e9af428 |
| image_feature_extraction.html | 30.5 kB | | 35f6dc51 |
| image_feature_extraction.md | 4.51 kB | | c1fea262 |
| image_text_to_text.html | 64.2 kB | | bdfa266b |
| image_text_to_text.md | 17.1 kB | | 9d9752ad |
| instance_segmentation.html | 74.3 kB | | b8539f04 |
| instance_segmentation.md | 18 kB | | a70db771 |
| keypoint_detection.html | 26 kB | | b27ebc03 |
| keypoint_detection.md | 5.21 kB | | d5a34483 |
| keypoint_matching.html | 23.7 kB | | 47a0e1ae |
| keypoint_matching.md | 4.4 kB | | 025aca87 |
| knowledge_distillation_for_image_classification.html | 31.7 kB | | 2d6feaf2 |
| knowledge_distillation_for_image_classification.md | 7.78 kB | | 0b0f3428 |
| language_modeling.html | 62.5 kB | | 10d5e7d3 |
| language_modeling.md | 14 kB | | 2995d1e8 |
| mask_generation.html | 80 kB | | 3403429a |
| mask_generation.md | 17.1 kB | | 43758a8a |
| masked_language_modeling.html | 63.4 kB | | 137d03ea |
| masked_language_modeling.md | 13.6 kB | | e45962e8 |
| monocular_depth_estimation.html | 29.5 kB | | 371fe54d |
| monocular_depth_estimation.md | 5.78 kB | | af2af164 |
| multiple_choice.html | 51.4 kB | | 176a1398 |
| multiple_choice.md | 9.41 kB | | e1b13ae3 |
| object_detection.html | 92 kB | | 7c8801b0 |
| object_detection.md | 22.8 kB | | 825cd73e |
| prompting.html | 45.6 kB | | 4b3e48bf |
| prompting.md | 13.4 kB | | c57e0ba8 |
| question_answering.html | 54.8 kB | | b62fd4d9 |
| question_answering.md | 11.3 kB | | d820d035 |
| semantic_segmentation.html | 107 kB | | ea1eed6e |
| semantic_segmentation.md | 21.3 kB | | a4782b44 |
| sequence_classification.html | 53.9 kB | | dfe5eabe |
| sequence_classification.md | 10.3 kB | | fe8f520b |
| summarization.html | 60.4 kB | | 718e73b3 |
| summarization.md | 17.7 kB | | c028aff8 |
| text-to-speech.html | 127 kB | | 926860a6 |
| text-to-speech.md | 23.6 kB | | f99d74dc |
| token_classification.html | 73.1 kB | | 0c40c3f4 |
| token_classification.md | 13.9 kB | | f68559e9 |
| training_vision_backbone.html | 35.9 kB | | 7eea4cb5 |
| training_vision_backbone.md | 8.7 kB | | a2f341ec |
| translation.html | 54.2 kB | | 61625caf |
| translation.md | 10.4 kB | | f5fa4971 |
| video_classification.html | 89.5 kB | | ac3011c5 |
| video_classification.md | 20.8 kB | | 53d2e1ac |
| video_text_to_text.html | 25.2 kB | | 03f4d9ca |
| video_text_to_text.md | 6.01 kB | | 09fa3330 |
| visual_document_retrieval.html | 27 kB | | 90671845 |
| visual_document_retrieval.md | 5.68 kB | | a0dbe13a |
| visual_question_answering.html | 69.9 kB | | 26bbf950 |
| visual_question_answering.md | 14.8 kB | | ecede442 |
| zero_shot_image_classification.html | 29.7 kB | | 96181919 |
| zero_shot_image_classification.md | 5.05 kB | | f1f5fb59 |
| zero_shot_object_detection.html | 57.4 kB | | cf79d4ec |
| zero_shot_object_detection.md | 10.4 kB | | 402e9230 |