Creating fine-tuned GPT-3 models via the OpenAI fine-tuning API скачать в хорошем качестве

Creating fine-tuned GPT-3 models via the OpenAI fine-tuning API

The GPT-3 language models have a range of impressive capabilities; however, they also have a number of performance limitations. In this talk OpenAI researcher, Todor Markov, discusses a new fine-tuning API by OpenAI and provides examples of its applications in creating specialized models. Todor Markov is a researcher on the Applied AI team at OpenAI. His current work focuses on improving the safety & monitoring system for the OpenAI API. Chapters: 0:00 - Introduction 2:00 - GPT-3 and the OpenAI API 5:20 - OpenAI fine-tuning API 6:30 - Live demo of the fine-tuning API in action 21:42 - Lessons (re-) learned: users, their preferences, obstacles, and prioritization 30:00 - Q&A Join Buzzrobot Slack community to connect with fellow data scientists, ML engineers and researchers: https://buzzrobot.slack.com/join/shar...