Finnish-NLP/llama-7b-finnish-instruct-v0.2

— This is 0.2 version release of our Instruct finetuned model from https://huggingface.co/Finnish-NLP/llama-7b-finnish — Model was trained for 3 epochs using 21946 samples and for this release we chose checkpoint at 8000 steps. — Future DPO/SFT+DPO variants are in the pipeline. Also we are investigating and testing different merging techiques For finetuning we try to select well known and widely used dataset and then filter/translate those with multiple methods: For this version we used a mix 21946 samples in total from the the following datasets: — LIMA from https://github.com/TurkuNLP/finnish-instructions — Dolly from https://github.com/TurkuNLP/finnish-instructions — OASST from https://github.com/TurkuNLP/finnish-instructions — Ultrafeedback http

Модальности:
Генерация текста

Области применения:
Следование инструкциям

Задача: Генерация текста
Автор: Finnish-NLP
Теги: llama, finnish, text-generation-inference, endpoints_compatible
Лайков: 3  |  Загрузок: 27

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.