SIGN IN SIGN UP
rasbt / LLMs-from-scratch UNCLAIMED

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

0 0 68 Jupyter Notebook

fix: correct role of the beta hyperparameter on the DPO loss (#818)

Increasing beta leads to less divergence between the new model and the reference model.
A
Andreas Yin committed
8e170312fec72450ab41d9232a143a2677afe5a4
Parent: 32965e0
Committed by GitHub <noreply@github.com> on 9/13/2025, 1:21:38 AM