𝐖𝐚𝐫𝐦 𝐢𝐧𝐯𝐢𝐭𝐚𝐭𝐢𝐨𝐧 𝐭𝐨 𝐣𝐨𝐢𝐧 𝐨𝐮𝐫 𝟒𝐭𝐡 𝐓𝐞𝐜𝐡 𝐓𝐚𝐥𝐤 𝟐𝟎𝟐𝟑 𝐀𝐈𝐄𝐈𝐱 𝐍𝐕𝐈𝐃𝐈𝐀 𝐨𝐧 "𝑬𝒇𝒇𝒊𝒄𝒊𝒆𝒏𝒕𝒍𝒚 𝒑𝒓𝒆-𝒕𝒓𝒂𝒊𝒏𝒊𝒏𝒈 𝑳𝑳𝑴 & 𝒇𝒊𝒏𝒆 𝒕𝒖𝒏𝒊𝒏𝒈 𝒇𝒐𝒓 𝒅𝒐𝒘𝒏𝒔𝒕𝒓𝒆𝒂𝒎 𝒕𝒂𝒔𝒌𝒔"
Our virtual talk of this episode was about large language models (LLM) which are made of billions of parameters and open a wide range of new applications, including natural language processing, human-machine interactions, generative AI, and healthcare applications. It showed the three-week journey to train an LLM model at scale and deploy it in a multi-node environment and how to use prompt tuning to adapt the model for different downstream tasks.
This talk was held by Dr. Johan Barthélemy (Developer Relation Manager at NVIDIA)
Date: March 14, 2023
Time: 10.30 AM - 12.00 PM (GMT+7)