sshh12/multi_token

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

2 best points · 0 comments · 1 Hacker News post · 187 GitHub stars · View on GitHub

Hacker News discussions

• Embed arbitrary modalities (images, audio, documents, etc.) into LLMs (2 points, 0 comments, by pyinstallwoes, 2023-12-18)