Function _log1mexp

src/post_training/dpo.py:43–45

Numerically stable log(1 - exp(x)) for x < 0.

(x: torch.Tensor)

def _log1mexp(x: torch.Tensor) -> torch.Tensor:
    """Numerically stable log(1 - exp(x)) for x < 0."""
    return torch.where(x > -0.6931, torch.log(-torch.expm1(x)), torch.log1p(-torch.exp(x)))


def orpo_loss(