ricecake/Orca-2-13B-Pygmalion-LoRA - Каталог нейросетей
Генерация текста

ricecake/Orca-2-13B-Pygmalion-LoRA

Добавлено:

++ This model’s response was too short, so I re-trained it, check this out: https://huggingface.co/ricecake/Orca-2-13B-Pyg-and-Bluemoon This LoRA adapter is a fine-tuned version of microsoft/Orca-2-13b on the PygmalionAI/PIPPA dataset. It achieves the following results on the evaluation set: — Loss: 1.9190 The following hyperparameters were used during training: — learningrate: 0.0002 — trainbatchsize: 1 — evalbatchsize: 1 — seed: 42 — gradientaccumulationsteps: 2 — totaltrainbatchsize: 2 — optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 — lrschedulertype: cosine — lrschedulerwarmupsteps: 10 — numepochs: 1 — Transformers 4.35.1 — Pytorch 2.1.0+cu121 — Datasets 2.14.7 — Tokenizers 0.14.1

Модальности:
Генерация текста


Задача: Генерация текста
Автор: ricecake
Теги: llama, generated_from_trainer, en, endpoints_compatible, 4-bit, bitsandbytes
Лайков: 2  |  Загрузок: 11

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.