To gain competitive advantage, innovative companies are starting to embed large language models into proprietary workflows that support domain-specific use cases. Many of them choose open-source LLMs to reduce data and compute requirements as well as privacy risks. The results have the potential to accelerate and enrich all sorts of business functions, from customer service to document processing and more. Join the discussion with AI leaders to understand how careful design, implementation, and governance will help you achieve success with generative AI.
Topics include:
Hear from AI industry leaders:
VP of Research at Eckerson Group
AI Product Director at Intel's Data Center and AI Group
Generative AI Marketing Lead at Intel's Data Center and AI Business Unit
The fast path to integrate the power of generative AI for your business is not necessarily general purpose, third-party giant models! Smaller LLM models, like those less than 20B parameters, can be a good or better match for your needs. Recent commercially available compact models, such as Llama 2, can address the key attributes that you need– performance, domain adaptation, private data integration, verifiability of results, security, flexibility, accuracy, and cost effectiveness. Join us as we evaluate the effectiveness of open source LLM models, discuss pros and cons, and share methods to build nimble models.
What you’ll learn about nimble models:
Vice President and Director of Emergent AI Research at Intel Labs, leading the development of third-wave AI capabilities.
NLP Deep Learning Researcher at EAI Intel Labs, specializing in Retrieval-Augmented Generation techniques.
Generative AI Marketing Lead at Intel's Data Center and AI Business Unit
There are multiple ways to create a domain specific LLM. Prompt engineering is a method to guide the model to a better output, while RAG augments the model with more data. Neither methods will change the models but both will improve the output. Come learn about the pros and cons of each method to achieve your business project objectives.
Speaker: Eduardo Alvare