Comet, a leading MLOps platform, launched of a new initiative to help data scientists and software engineers keep pace with the changing world of Large Language Models (LLMs) and all of the possibilities they can enable. In a new course, taught by co-founder of DAIR.AI, Elvis Saravia, Comet breaks down the process of building LLMs for the real world with practical examples and use cases, such as how to build a reliable customer support chatbot, how to construct a clickbait detector from scratch, and how to deploy an LLM-powered evaluation system. The course also reveals the latest trends in LLMs and shows participants how to operationalize them. The course, LLMOps: Building Real-World Applications With Large Language Models is available, free of charge.
“LLMs are changing the world, and data scientists and software engineers must keep up,” said Saravia. “We designed a course that will teach participants exactly how to build modern software with LLMs, using the newest tools and techniques. It’s everything you need to know to take a big leap forward.”
Practical Learning Experiences
Comet introduced the industry’s only course completely focused on building real-world applications with LLMs. While it covers some theory, it is first and foremost a course in applied AI, not mathematics. Its six modules, each of which has a notebook attached for hands-on learning, include:
- Module One: Introduction to LLMOps
- Module Two: Working With LLMs
- Module Three: LLMOps in Practice
- Module Four: Case Studies & Applications of LLMOps
- Module Five: Advanced Topics in LLMs and LLMOps
- Module Six: The Future of LLMOps
Course participants can also seek help, ask questions, or engage in more in-depth conversations by joining the course Slack community.
Upon course completion, participants will be able to choose and finetune an LLM for their specific needs. They’ll also understand how to get the most out of an LLM from prompt engineering to model evaluation and will be able to build LLM-powered applications with vector databases and other tools. Notably, participants learn how to prevent bias from seeping into their LLM as well as how to combat bad actors.
Finding Solutions
Comet has long been committed to furthering MLOps and educating the broader community so that businesses can achieve the value they seek. Collaborating with enterprise customers like Uber, Netflix, Shopify, Etsy, and scores of others, Comet understands where pain points exist across the MLOps spectrum. This course is one of many solutions Comet has put forth to address existing challenges.
“Everyone from data science practitioners to executive team members are focused on using LLMs, but they’re not thinking about operationalizing them,” said Gideon Mendels, CEO and co-founder of Comet. “How do you keep track of all your prompts? How do you keep track of all the different LLMs you’re trying to evaluate? And how do you deploy and ultimately monitor your LLMs? Those things matter, but not many people consider such questions. Comet’s Building With LLMs course brings that information to the forefront so that data scientists and software engineers can be successful.”
In addition to its latest course offering, Comet has added a new Prompt Engineering tool to its platform: CometLLM. CometLLM helps developers log and visualize their LLM prompts and chains. Users can also search for specific prompts, add token usage as prompt metadata, and give prompt feedback.
Meet the Instructor
Savaria is well known in LLM circles, as he leads all AI research, education, and engineering efforts at DAIR.AI, the company he co-founded. His primary interests are training and evaluating large language models and developing applications on top of them. Savaria is also the co-creator of the Galactica LLM and was a technical product marketing manager at Meta AI where he supported and advised world-class teams like FAIR, PyTorch, and Papers with Code. Prior to this, he was an education architect at Elastic where he developed technical curriculum and courses.
The Details
LLMOps: Building Real-World Applications With Large Language Models is geared towards intermediate level data scientists and software engineers with basic knowledge of ML as well as Python experience. Participants can expect to complete the course in approximately two weeks. To get started, please click here.
Sign up for the free insideAI News newsletter.
Join us on Twitter: https://twitter.com/InsideBigData1
Join us on LinkedIn: https://www.linkedin.com/company/insidebigdata/
Join us on Facebook: https://www.facebook.com/insideAI NewsNOW