Use open models

You can use open models with Vertex AI. An open model is freely available, you are free to publish its outputs, and it can be used anywhere provided you adhere to its licensing terms. When you use an open model with Vertex AI, you use Vertex AI for your infrastructure. You can also use open models with other infrastructure product, such as PyTorch or Jax. Open models shouldn't be confused with open source models because open models don't necessarily provide source code and information to train the model from scratch.

Many open models are considered open weight large language models (LLMs). Open models provide more transparency than models that aren't open weight. A model's weights are the numerical values stored in the model's neural network architecture that represent learned patterns and relationships from the data a model is trained on. The pretrained parameters, or weights, of open weight models are released. You can use an open weight model for inference and tuning while details such as the original dataset, model architecture, and training code aren't provided.

Details about an open model and how to use it are on its model card in Model Garden. To access the model card of an open model, go to Model Garden and search for its name. For more information about Model Garden, see Explore AI models in Model Garden.

To learn how to use Gemma and Llama open models see the following: