Deploy open models with TGI on Cloud Run

Опубликовано 7 ноября 2024, 17:00

Tutorial: How to deploy Gemma 2 on Cloud Run with TGI → goo.gle/3Yoztjh
Get started with Cloud Run GPU → goo.gle/4ec7mJS
Docs: Text Generation Inference → goo.gle/4e7qusz

Start serving text generation inference with fast token speed and serve requests for a fraction of the cost of traditional methods. Watch along and learn how to deploy the Gemma 2 model to Cloud Run using Hugging Face TGI with Wietse Venema (Google) and Alvaro Bartolome (Hugging Face).

More resources:
Gemma 2 (9b) on the Hugging Face Hub → goo.gle/3C1vX6R
Hugging Face Deep Learning Containers for Google Cloud → goo.gle/3BPaYUM

Watch more Google Cloud: Building with Hugging Face → goo.gle/BuildWithHuggingFace
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#GoogleCloud #HuggingFace

Speakers: Wietse Venema, Alvaro Bartolome
Products Mentioned: Gemma, Hugging Face, Cloud Run