A Practical Guide to Efficient AI
December 07, 2024
30 min
Free
ai
artificial-intelligence
machine-learning
llm
large-language-models
model-optimization
quantization
small-language-models
function-calling
prompt-engineering
inference
model-efficiency
Description
In this talk, Dr. Shelby Heinecke, Senior AI Research Manager at Salesforce, explores key sources of inefficiency in AI models and discusses practical techniques and tools to improve efficiency. Topics covered include model architecture selection, quantization, and prompt optimization. The presentation highlights the importance of efficient AI for deploying models at scale in resource-constrained environments, from cloud to on-device, and showcases advancements in small language models and function calling capabilities.