How to fine-tune a base LLM for RAG with DeciLM-6B and LLMWare
Powered by Restream https://restream.io
As retrieval augmented generation (RAG) has emerged as a leading paradigm for deploying generative AI in the enterprise, there has been a growing interest in applying smaller, open-source, fine-tuned models as part of an RAG workflow.
In this webinar, Deci, in conjunction with Ai Bloks, will show how to leverage the Deci LM-6B LLM, fine-tuned for RAG, and integrate into an RAG workflow using Ai Bloks’ open source library, llmware. Everything will be open source and deployable in a private cloud.
We will focus on use cases in financial services, legal and compliance, which tend to have complex and sensitive information requirements and many high-value applications of Generative AI.
The webinar will be hands-on with code samples and will highlight each component of this state-of-the-art open-source RAG system, as well as how to get started customizing for your workflows.