[BUG] Use sampling for greedy mode

[tonysy]

Describe the bug

A clear and concise description of what the bug is.

lighteval/src/lighteval/models/vllm/vllm_model.py

Line 281 in d6de1fe

vllm_outputs = self._generate(

The generate is True if this call does not give the generate parameter. Then the _generate will use the default temperature=1.0 for decoding.

To Reproduce

Please provide all the steps needed to reproduce the behavior, or provide a minimal working example if needed. We will ignore issues missing this section.

Expected behavior

A clear and concise description of what you expected to happen.

Version info

Please provide your operating system, lighteval version or commit if you installed from main, and pip/conda environment if your problem concerns dependencies.