Taming AI or how we build the alignment pipeline

Webinar by LLMOps.Space with Maksim Nekrashevich, ML & LLM Engineer at Nebius AI.

The session is dedicated to key aspects of aligning LLMs and explores how to set up the necessary infrastructure to maintain a versatile alignment pipeline.

We will cover reinforcement learning with human feedback (RLHF), prompt tuning and AI workflow management.

July 11, Thursday, 17:00 (UTC+2)

During this session, we will cover:

  • Incorporating LLMs into the data collection for supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to maximize efficiency.
  • Techniques for instilling desired behaviors in LLMs through the strategic use of prompt tuning.
  • An exploration of cutting-edge workflow management and how it facilitates rapid prototyping of highly-intensive distributed training procedures.

Try Nebius AI console today

Get immediate access to up to 8 NVIDIA® GPUs, along with CPU resources, storage and additional services through our user-friendly self-service console.