Training and using large language models (LLMs) is expensive due to their large compute requirements and memory footprints. This article will explore how…
Weaviate now supports the PaLM models for embeddings and generative search through two new modules.
We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset of these (imperfect) explanations and scores for every neuron in GPT-2.
Learn the top 3 takeaways for building responsible AI from AI risk expert Patrick Hall, including tips for model risk management, model governance, and AI fairness.
An introduction to creating generative feedback loops with LLMs in Weaviate.
Weaviate 1.19 introduces generative cohere module, gRPC API support, improved data types, and more.