Fine-tuning of LLMs in Amazon SageMaker JumpStart
In this code walk-through, we will discuss mechanisms to build a human-feedback workflow to further fine-tune and improve our model.
In this code walk-through, we will discuss mechanisms to build a human-feedback workflow to further fine-tune and improve our model. We demonstrate how to incorporate the human feedback back into the fine-tuning pipeline with reinforcement learning (RLHF).