diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 1b2f348541..f36598b0ac 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -94,6 +94,7 @@ from typing import * from dataclasses import dataclass, field from packaging.version import Version import torch +import numpy as np from contextlib import nullcontext from torch.nn import functional as F torch_compile_options = {{