Google AI:DEV 作者專屬· Laurent Picard·· 9 天前AI 評分24
甚麼是 Gemini 的原生多模態?
🎞️ What is native multimodality?
AI 導讀
Gemini 處理多模態輸入時會涉及三種 tokenizer,分別處理文字、視覺和音訊。內容探討這三種 tokenizer 如何協同運作。
正文
🍿 Just a moment #01
Did you know there are three tokenizers involved when Gemini processes multimodal inputs? In this episode, we peek under the hood to see how text, vision, and audio tokenizers work together.
More
- 🔗 Explore Gemini models → https://g.dev/cloud/gemini-models
- 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
來源:Google AI:DEV 作者專屬 · dev.to