Machine Learning Spain (LI)

¡Machine Learners! 👋

¡Estamos de vuelta! Estábamos deseando que el calor nos diese una tregua para volver a encontrarnos.

Nos vemos este jueves 15 de septiembre a las 18.30h en riguroso directo desde el espacio StageONE de SNGULAR, en un modelo híbrido: speakers, organización e invitados presenciales en el estudio (necesitamos confirmación para gestionar la entrada), y demás asistentes en virtual vía youtube (a través del canal Machine Learning Spain.

Conversaremos y nos pondremos al día después de un periodo largo de silencio involuntario.

Agenda a día de hoy.... (siempre puede haber sorpresas y cambios de última hora, ya sabéis, aquí es impredecible)

✔️ 18.30h Miguel Martínez, Senior Deep Learning Data Scientist at NVIDIA

Building Large-scale, Localized Language Models: From Data Preparation to Production

Abstract:
Recent advances in natural language processing demonstrate the capability of large-scale language models (such as GPT-3) to solve a variety of NLP problems with zero shots shifting from supervised fine-tuning to prompt engineering/tuning. However, building large language models raises data preparation, training, and deployment challenges. In addition, while the process is well-established for a few dominant languages such as English, its execution in localized languages remains limited. We'll give an overview of the end-to-end process for building large-scale language models, discuss the challenges of scaling, and describe some existing solutions for efficient data preparation, distributed training, model optimization, and distributed deployment. We'll use examples in localized languages such as French or Spanish using NVIDIA Nemo Megatron, a framework for training large NLP models optimized for SuperPOD hardware infrastructure.

✔️ 19.30h Presentación del meetup tinyML y novedades al respecto.

✔️ Tras las charlas, nos tomaremos unas cerves para seguir conversando :)

¡Os esperamos! Y si es presencial, mejor que mejor, que ya hay ganas de verse.