This model is fine-tuned version of google/flan-t5-small for question generation task on the lmqg/qgsquad (datasetname: default) via lmqg. — Language model: google/flan-t5-small — Language: en — Training data: lmqg/qgsquad (default) — Online Demo: https://autoqg.net/ — Repository: https://github.com/asahi417/lm-question-generation — Paper:** https://arxiv.org/abs/2210.03992 — Metric (Question & Answer Generation, Pipeline Approach): Each question is generated on the answer generated by lmqg/flan-t5-small-squad-ae. raw metric file The following hyperparameters were used during fine-tuning: — datasetpath: lmqg/qgsquad — datasetname: default — inputtypes: paragraphanswer — outputtypes: question — prefixtypes: [‘qg’] — model: google/flan-t5-small — maxlength: 512 — maxlengthoutput: 32 — epoch: 7 — batch: 64 — lr: 0.0001 — fp16: False — randomseed: 1 — gradientaccumulationsteps: 1 — labelsmoothing: 0.15 The full configuration can be found at fine-tuning config file.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: lmqg
Теги: t5, text2text-generation, question generation, en, model-index, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 27
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
