Responsible AI: A guide to guardrails and scorers
The rapid adoption of generative AI and large language models has transformed industries, enabling powerful applications in domains like customer service, content creation, and research. However, this innovation introduces risks related to misinformation, bias, and privacy breaches. To ensure AI operates within ethical and functional boundaries, organizations must implement AI guardrails – structured safeguards that […]
Generative AI in retail
Generative AI is reshaping the retail industry, ushering in a new era of personalization, operational efficiency, and innovation. As this technology advances, retailers are leveraging it to anticipate customer needs, enhance service quality, and streamline their operations—all of which are crucial in today’s competitive landscape. By delivering tailored experiences and automating complex processes, generative AI […]
Current best practices for training LLMs from scratch
Download the PDF On this page Introduction The scaling laws Hardware Dataset collection Dataset pre-processing Pre-training steps Model evaluation Bias and toxicity Instruction tuning RLHF Conclusion References Appendix Introduction Although we’re only a few years removed from the transformer breakthrough, LLMs have already grown massively in performance, cost, and promise. At W&B, we’ve been fortunate […]
What is retrieval augmented generation?
Retrieval-Augmented Generation (RAG) is a powerful technique in AI that combines large language models with real-time access to external data sources, allowing for more accurate, relevant, and timely responses. By dynamically retrieving authoritative information, RAG enables generative models to overcome the limitations of static, pre-trained knowledge, making them more effective for applications where precision and […]
RAG techniques: From naive to advanced
Imagine you’re demoing your company’s new AI chatbot to a potential client. You ask it about their latest product, the one they’ve been working on for months, and what does it return? Information from two years ago about a product they don’t even sell anymore. Frustrating, right? This is a good example of what retrieval […]
AI and regulatory compliance in finance
In the complex world of finance, where numerous transactions and exchanges occur every second, there is a crucial framework in place to ensure everything operates smoothly: regulatory compliance. Regulatory compliance is about following the established laws and guidelines to keep the financial market safe and fair for everyone. This ensures that banks and other financial […]
What is model risk management in finance?
In the fast-paced world of finance, the use of models has become incredibly important for making big decisions. These models help banks and other financial institutions figure out risks, value things like stocks or bonds, and predict future market trends. But as much as these models can help, they also bring a certain level of […]
What is an ML Model Registry?
On this page What is a model registry in ML? Benefits of an ML Model Registry Where does a data and model registry fit in your MLOps stack? The Weights & Biases Registry Exploring the Benefits of W&B Registry How to Get Started with the W&B Registry Conclusion In the rapidly changing landscape of machine […]
Intro to MLOps: Machine learning experiment tracking
On this page What is Experiment Tracking in Machine Learning? Why Do You Need to Track Your ML Experiments? How Do You Track Machine Learning Experiments? Conclusion Imagine you are trying to develop a recipe for the best chocolate chip cookies. After the first try, you might increase the amount of flour. One time, you […]
Intro to MLOps: Hyperparameter tuning
On this page What a hyperparameter actually is Why tuning matters Which settings usually matter most How people search for good values The rule that protects your final score What W&B changes The experiment and what it showed How to reproduce the sweeps What to remember Introduction A lot of machine learning work looks harder […]