sshh12/multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.

语言：Python · GitHub 星标：187 · Fork：17

话题：large-context · large-language-models · large-multimodal-models · llava · llm · multi-modality · multimodal · vision-language-model

在 GitHub 上查看原仓库