Open-source native vision-language models (NEO series) that process pixels and words in one encoder-free dense architecture, with 2B and 9B releases.
9030PythonApache-2.0Atualizado há 3 meses
#multimodal-large-language-models
Repositórios do GitHub selecionados relacionados a multimodal-large-language-models, com resumos de IA e métricas principais.
Open-source native vision-language models (NEO series) that process pixels and words in one encoder-free dense architecture, with 2B and 9B releases.