This repository features LLaVA v1.5 trained with the Phi-3-mini-3.8B LLM. This integration aims to leverage the strengths of both models to offer advanced vision-language understanding. — Only Vision-to-Language projector is trained. The rest of the model is frozen. — Note: The repository contains only the projector weights. — Base Large Language Model (LLM): Phi-3-mini-4k-instruct — Base Large Multimodal Model (LMM): LLaVA-v1.5
Модальности:
Генерация текста
Области применения:
Следование инструкциям
Задача: Генерация текста
Автор: MBZUAI
Теги: llava_phi, custom_code, endpoints_compatible
Лайков: 3 | Загрузок: 27
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.