You can get started in 4 ways:
Run it locally
Select which TxGemma variant you want to use, download it from Hugging Face and run it locally.
This is the recommended option, if you want to experiment with the model and don't need to handle a high volume of data. Our GitHub repository includes a notebook that you can use to get started with TxGemma.
We have two other notebooks:
- Finetune with Hugging Face which shows how you can finetune TxGemma.
- Agentic-Tx Demo which has an example agentic implementation of TxGemma. You'll need a Gemini API key to run this.
Deploy your own online service
TxGemma can be deployed as a highly available and scalable HTTPS endpoint on Vertex AI. The easiest way is through Model Garden.
This option is ideal for production-grade, online applications with low latency, high scalability and availability requirements. Refer to Vertex AI's service level agreement (SLA) and pricing model for online predictions.
A sample notebook is available to help you get started quickly.
Launch a batch job
For larger dataset in a batch workflow, it's best to launch TxGemma as a Vertex AI batch prediction job. Note that Vertex AI's SLA and pricing model are different for batch prediction jobs.
Refer to the "Get batch predictions" section in the Quick start with Model Garden notebook to get started.
Contact
Here are the best ways to engage with our team and the community:
- Seek technical support on the HAI-DEF developer forum.
- File technical issues directly on GitHub.
- Help shape our roadmap by sharing your use cases using our feedback form. This helps us align our engineering efforts with the industry's most common needs.
- Stay updated on new tools and models by signing up for our newsletter.