Published
Building multilingual AI applications is crucial for reaching global audiences, and varied language proficiency remains a top developer priority. In this talk, we’ll explore the training strategies applied to make Gemma 3 fluent in over 100 languages, and showcase its state-of-the-art performance on multilingual tasks.
Subscribe to Google for Developers → https://goo.gle/developers
Speakers: Adi Mayrav Gilady
Products Mentioned: Gemma
Subscribe to Google for Developers → https://goo.gle/developers
Speakers: Adi Mayrav Gilady
Products Mentioned: Gemma
- Category
- Project
- Tags
- Google, developers, pr_pr: Gemma;
Sign in or sign up to post comments.
Be the first to comment
Up Next
-
14:29
What's new in Gemma 2
-
09:36
Gemma 3 architecture and design
-
00:35
Top 3 use cases for retraining Gemma?
-
08:12
Demo: JAX, Flax and Gemma
-
07:24
Demo: Gemma Scope: Sparse autoencoders on Gemma 2
-
26:21
Hands-on introduction to Gemma
-
06:31
Gemma in Minutes: 3 ways to run Gemma’s latest version!
-
04:21
What’s new in Gemma 3?
-
00:15
Run AI locally, with Gemma!
-
12:10
Get started with Gemma 3 on Vertex AI
-
09:35
AI for everyone with Gemma
-
13:40
Building for a multilingual world
-
11:51
Gemma: The responsible way to build
-
01:02
Hugging Face + Gemma = ????
-
06:39
Welcome to Gemma 3
-
09:27
Using and fine-tuning Gemma 3
-
26:48
Deepdive into Gemma 3
-
01:51
What is Gemma Scope?
-
00:27
What Gemma model can help me code?
-
01:01
Biggest updates in Gemma 2
-
09:00
Getting started with Gemma models
-
04:12
Which Gemma version is the right one for you?
Loading...