180. Min-P Sampling Filter

Easy

Implement the min-p truncation filter for next-token sampling.

Signature: def min_p_filter(probs: np.ndarray, min_p: float) -> np.ndarray

Assume probs is already a valid distribution (non-negative, sums to 1).

Math

\overset{p}{^}_{i} = \frac{p _{i} \cdot 1 [ p _{i} \geq m \cdot p _{m a x} ]}{\sum _{j} p _{j} \cdot 1 [ p _{j} \geq m \cdot p _{m a x} ]}

Asked at

NumPy

import numpy as np

def min_p_filter(...):

pass

Premium problem

Free accounts include problems #1–20. Upgrade to unlock the editor, hidden test cases, and reference solutions for every problem.

Already premium?