AI on Pi Day Highlights

We are excited to announce a new column in our Forecaster article where we’ll be showcasing our sessions! You’ll find them listed in chronological order, and as a bonus, we’ll be providing some complimentary gifts. To find them, just check the presentation links. Easy peasy!

Building LLM apps with LLama CPP in 15 minutes by Nicholas Renotte

Imagine having your own personal AI assistant, ready to answer your questions, summarize data, or even generate creative text formats – all on your local machine. This isn’t science fiction; it’s becoming a reality with open-source tools like Llama++. In session on our Pi Day, Nicholas Renotte, demonstrated the power of Llama++. This clever library is a real game-changer! It allows you to create a fake OpenAI server, essentially running your own large language models (LLMs) without relying on external services. The session showcased a Python script built by Renotte that interacts with this local LLM server. By sending prompts and receiving responses, the script can perform various tasks, from stock price analysis to creative writing. But Renotte doesn’t stop at the code. He emphasises the importance of a user-friendly interface, making it easier for everyone to use. By integrating the script with a Streamlit app, he creates a visually appealing platform for anyone to interact with the LLM. It’s a great way to engage with the technology! The presentation delved deeper into the critical aspects of AI governance and explainability. As LLMs become more powerful, ensuring responsible use and understanding how they generate responses is paramount. He really emphasised the importance of adapting evaluation metrics to specific use cases, and said there’s no one-size-fits-all approach.

The live coding session finished with a Q&A, where Renotte talked about the future of AI. He thinks that explainability and governance will be really important in the coming years, along with the ongoing advancements and miniaturisation of LLM technology.

This session is a great inspiration for anyone curious about AI. By using open-source tools like Llama++, you can build your own AI playground, which is a great way to gain a deeper understanding of this rapidly evolving field. Watch the video.

We work on

Bitol is a Linux Foundation AI & Data Sandbox project licensed under the Apache 2.0 license. As of now, it defines an open standard for data contracts called Open Data Contract Standard.

Share and Stay Tuned

Become a Member if you want to be a part of the story.

Share Events and News you find interesting with us here! We will give it a shout on our new newsletter AIDA Forecaster!

For exciting updates and valuable insights, visit us at aidausergroup.org and on LinkedIn. Stay tuned for more!

Leave a Reply