Accountable by design
Gemma is designed with our AI Ideas on the forefront. As a part of making Gemma pre-trained fashions secure and dependable, we used automated strategies to filter out sure private data and different delicate knowledge from coaching units. Moreover, we used intensive fine-tuning and reinforcement studying from human suggestions (RLHF) to align our instruction-tuned fashions with accountable behaviors. To grasp and cut back the danger profile for Gemma fashions, we carried out sturdy evaluations together with handbook red-teaming, automated adversarial testing, and assessments of mannequin capabilities for harmful actions. These evaluations are outlined in our Mannequin Card.
We’re additionally releasing a brand new Accountable Generative AI Toolkit along with Gemma to assist builders and researchers prioritize constructing secure and accountable AI functions. The toolkit consists of:
- Security classification: We offer a novel methodology for constructing sturdy security classifiers with minimal examples.
- Debugging: A mannequin debugging instrument helps you examine Gemma’s habits and tackle potential points.
- Steering: You’ll be able to entry finest practices for mannequin builders primarily based on Google’s expertise in growing and deploying massive language fashions.
Optimized throughout frameworks, instruments and {hardware}
You’ll be able to fine-tune Gemma fashions by yourself knowledge to adapt to particular utility wants, reminiscent of summarization or retrieval-augmented era (RAG). Gemma helps all kinds of instruments and methods:
- Multi-framework instruments: Deliver your favourite framework, with reference implementations for inference and fine-tuning throughout multi-framework Keras 3.0, native PyTorch, JAX, and Hugging Face Transformers.
- Cross-device compatibility: Gemma fashions run throughout in style system varieties, together with laptop computer, desktop, IoT, cellular and cloud, enabling broadly accessible AI capabilities.
- Reducing-edge {hardware} platforms: We’ve partnered with NVIDIA to optimize Gemma for NVIDIA GPUs, from knowledge middle to the cloud to native RTX AI PCs, guaranteeing industry-leading efficiency and integration with cutting-edge know-how.
- Optimized for Google Cloud: Vertex AI supplies a broad MLOps toolset with a variety of tuning choices and one-click deployment utilizing built-in inference optimizations. Superior customization is offered with fully-managed Vertex AI instruments or with self-managed GKE, together with deployment to cost-efficient infrastructure throughout GPU, TPU, and CPU from both platform.
Free credit for analysis and improvement
Gemma is constructed for the open group of builders and researchers powering AI innovation. You can begin working with Gemma at this time utilizing free entry in Kaggle, a free tier for Colab notebooks, and $300 in credit for first-time Google Cloud customers. Researchers may apply for Google Cloud credit of as much as $500,000 to speed up their tasks.
Getting began
You’ll be able to discover extra about Gemma and entry quickstart guides on ai.google.dev/gemma.
As we proceed to increase the Gemma mannequin household, we sit up for introducing new variants for numerous functions. Keep tuned for occasions and alternatives within the coming weeks to attach, be taught and construct with Gemma.
We’re excited to see what you create!
