This is a Llama-2-13b-chat-hf model fine-tuned using QLoRA (4-bit precision). It was trained Colab Pro+. It is mainly designed for educational purposes, not for inference but can be used exclusively with BBVA Group, GarantiBBVA and its subsidiaries. Parameters:
Модальности:
Генерация текста
Задача: Генерация текста
Автор: emre
Теги: tensorboard, llama, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 12
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.