Building and Running a Scaling, Enterprise FinLLM Using OSS and Accelerated Computing

Open Source In Finance Forum 2024 - London
Presented by Jochen Papenbrock, NVIDIA
Title: Building and Running a Scaling, Enterprise FinLLM Using OSS and Accelerated Computing
Abstract: In this talk, Jochen presents various OSS tools from NeMo LLM Framework that can be leveraged on an accelerated computing platform for building scaling, enterprise-ready (Financial) LLMs with outstanding performance, accuracy, stability and guardrailed trustworthiness. Initial step is to select one of the best community-build LLMs like Llama, Falcon, Mixtral or Nemotron. Next steps is to use tools for model customization, retrieval augmented generation, and guardrailing. Then, the model will be deployed with an inference platform that is optimized for throughput and scale. Input data can be tokenized, curated, and deduplicated at scale.
You can find the slides here: osfflondon2024.sched.com/even...%&sidebar=yes&bg=no
Find more info about FINOS:
On the web: www.finos.org/
Twitter: x.com/finosfoundation
LinkedIn: / finosfoundation
OSFF London: events.linuxfoundation.org/op...