This model is a fine-tuned version of LLaMA-7b on human written translations and evaluation data, for only research use. For more details, please refer to the github repo: [[ParroT]](https://github.com/wxjiao/ParroT). The following hyperparameters were used during training: — learningrate: 2e-05 — trainbatchsize: 4 — evalbatchsize: 4 — seed: 1 — distributedtype: multi-GPU — numdevices: 32 — totaltrainbatchsize: 128 — totalevalbatchsize: 128 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: cosine — lrschedulerwarmupratio: 0.03 — num_epochs: 3.0 — Transformers 4.27.0.dev0 — Pytorch 1.10.0 — Datasets 2.10.0 — Tokenizers 0.13.2
Модальности:
Генерация текста
Задача: Генерация текста
Автор: wxjiao
Теги: llama, generated_from_trainer, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 15
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
