Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6. Original model: https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct To download the main (only useful if you only care about measurement.json) branch to a folder called LLaMA-Pro-8B-Instruct-exl2: To download from a different branch, add the —revision parameter:
Модальности:
Генерация текста
Области применения:
Следование инструкциям
Задача: Генерация текста
Автор: bartowski
Лайков: 3 | Загрузок: 2
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.