Enhanced Fine-tuning of Open Source Pre-trained LLMs for Q&A and SUM tasks

To access this webinar, please register here: https://hubs.li/Q01Xj2gm0

Topic: “Enhanced Fine-tuning (using PEFT) of Open Source Pre-trained LLMs for Q&A and Summarization Tasks”

Speaker: Dr. Sanjay Basu, Senior Director – AI/ML at Oracle Cloud Engineering
Dr. Sanjay Basu is a highly accomplished leader with superior strengths in setting technology direction, managing customer relationships, managing large, diverse teams and delivering results. He is an industry-recognized Artificial Intelligence / Machine Learning / Quantum Computing subject matter expert.

Abstract:
In the realm of Natural Language Processing (NLP) and Large Language Models (LLM), leveraging pre-trained models has become a transformative practice, accelerating both research and applications in real-world scenarios. Presented by Oracle Cloud Infrastructure and NVIDIA, this talk is intended to guide attendees on the path of fine-tuning large pre-trained models such as HuggingFace's Transformers (Falcon-40B), specifically focusing on question-answering and text summarization tasks.

We will delve into the theory and practical aspects of fine-tuning these models, shedding light on the mechanisms and strategies for model optimization and tailoring to specific tasks. Attendees will gain a deeper understanding of how pre-training and fine-tuning paradigms work and will acquire the know-how to apply them in their own NLP/LLM projects.

ODSC Links:
• Get free access to more talks/trainings like this at Ai+ Training platform:
https://hubs.li/H0Zycsf0
• ODSC blog: https://opendatascience.com/
• Facebook: https://www.facebook.com/OPENDATASCI
• Twitter: https://twitter.com/_ODSC & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science
• Slack Channel: https://hubs.li/Q01YzHZw0
• Code of conduct: https://odsc.com/code-of-conduct/