Back To Schedule
Friday, October 6 • 4:30pm - 6:00pm
Run LLMs On Your Laptop / Ejecuta LLMs en tu computadora

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Your laptop can run a large language model. Running language models locally means your interactions are absolutely private! It isn’t difficult. Learn how to install and use the required software in this comprehensive workshop. Along the way, discover key settings to optimize your output—and learn how to customize your very own chatbot prompt. Attendees will learn how to install and use llama.cpp, a comprehensive program for running language models on low-resource computers. They will learn how to manipulate the output of the program through temperature, grammars, context size, and prompts.

Tu portátil puede ejecutar un modelo de lenguaje grande. Ejecutar modelos de lenguaje de forma local significa que tus interacciones son completamente privadas. No es difícil. Aprende cómo instalar y utilizar el software necesario en este taller completo. En el proceso, descubre configuraciones clave para optimizar tus resultados y aprende cómo personalizar tu propio mensaje para un chatbot. Los asistentes aprenderán cómo instalar y utilizar llama.cpp, un programa completo para ejecutar modelos de lenguaje en computadoras con recursos limitados. Aprenderán a manipular la salida del programa a través de la temperatura, gramáticas, tamaño de contexto y mensajes de entrada.

avatar for Sil Hamilton

Sil Hamilton

Researcher-in-Residence, Hacks/Hackers
Sil Hamilton is AI researcher-in-residence at Hacks/Hackers. An AI researcher at McGill University exploring the intersection of code and culture, Sil has published at NLP conferences like ACL, AAAI, and COLING. His work exploring the limits of LLMs has been discussed by Wired, The... Read More →

Friday October 6, 2023 4:30pm - 6:00pm GMT-03
Sala de las Columnas 1