Tuning Gemma models: How much data?

Channel:
United States Google for Developers
Subscribers:
2,510,000
Published on ● Video Link: https://www.youtube.com/watch?v=cFxTXXkyxrI


Duration: 0:00
1,303 views
33

You can tune a Gemma model for a data extraction task with just 8 examples. How much data you need depends on the task, but it might not take as much data as you think!

Watch more Build with Google AI → https://goo.gle/BuildwithGoogleAI
Subscribe to Google for Developers → https://goo.gle/developers

#BuildwithGoogleAI #AI #Google

Speaker: Joe Fernandez
Products Mentioned: Gemma



Other Videos By Google for Developers


2024-10-18Demo: Gemma Scope: Sparse autoencoders on Gemma 2
2024-10-17Demo: Unleashing Gemma in production with Hugging Face Text Generation Inference (TGI)
2024-10-17Demo: Gemma 2 2B on a Jetson Orin Nano
2024-10-17How to run and scale Gemma 2 on Google Cloud
2024-10-16What Gemma model can help me code?
2024-10-15Personal AI Code Assistant with Gemma | Build with Google AI
2024-10-15AI Code Assistant with no third-party services required
2024-10-13Revolutionize how your team interacts with data!
2024-10-09Run AI locally, with Gemma!
2024-10-09Think you can hack Google? Lets find out.
2024-10-08Tuning Gemma models: How much data?
2024-10-07How long does it REALLY take to build an AI task assistant?
2024-10-07Business Email AI Assistant with Gemma | Build with Google AI
2024-10-03Gemma AI: language tuning short cut
2024-10-03Tips for tuning Gemma models for languages
2024-10-03Drive consistent conversion improvements with Google Pay
2024-10-03A gift card for you! How to create them with Google Wallet
2024-10-02Fine-tune language models with surprisingly little data!
2024-10-02Tune Gemma as a Spoken Language AI Assistant | Build with Google AI
2024-10-02Ethical practices in AI
2024-10-01Any advice for devs exploring AI?