Leveraging Large Language Models for Enterprise Usage

Organizations worldwide are still trying to understand how to leverage generative AI models and put them into practical use. To enable them, NVIDIA developed a full-stack approach, from the hardware to develop and serve these models, to the variety of customizable SDKs and services to assist research and industry alike. However, LLMs, like any other technology, are not perfect and require guardrails to address shortcomings such as hallucination, inherited bias, and toxicity. By providing toolsets and mechanisms to mitigate these limitations, in the roads ahead, we hope to see generative AI open up new horizons and brings about positive revolution. Join this talk to learn about foundation and ChatGPT-style models, generative AI and LLM technology at NVIDIA, shortcomings and proposed guardrails, and the road ahead.

Speaker:
Zenodia Charpy is a senior deep learning data scientist working at NVIDIA. Her field of expertise lies in training and deploying very large language models with a focus on tackling challenges for non-English and low-resource languages such as Swedish, Danish, Norwegian, and many others. Exploring parameter efficient tuning techniques to boost LLMs performance further while grounding factual correctness of LLMs responses.