LLM Meetup in Palo Alto

​Join us for an exciting event to discuss the latest advancements in large language models (LLMs) and how they are being used to power real-world applications. We will be focusing on Cresta's new Ocean-1 model, which has been shown to beat GPT-4 in retrieval-augmented generation (RAG) while being 100x more cost-effective.

​During the event, we will cover:

• ​The challenges of using LLMs in real-time voice applications

• ​How Cresta uses RAG to power its knowledge assist feature

• ​How Ocean-1 was trained on synthetic and customer-specific data

• ​The results of a benchmark comparing Ocean-1 to GPT-4

• ​How Cresta is using LoRA and Axolotl to improve its models continuously

• ​How Fireworks AI is helping Cresta scale its models to thousands of customers

​Agenda:

• ​5:30 PM - 6:00 PM: Arrival & Networking

• ​6:00 PM - 7:00 PM: Beating GPT-4 in RAG with domain-specific fine-tuning

• ​7:00 PM - 7:30 PM: Networking & Drinks