sampling_params.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Sampling parameters for text generation.
# Documentation: https://docs.vllm.ai/en/v0.6.4/dev/sampling_params.html

# To enable syntax highlighting: https://marketplace.visualstudio.com/items?itemName=redhat.vscode-yaml
# yaml-language-server: $schema=schemas/sampling_params.json

# Maximum number of tokens to generate per output sequence.
max_tokens: 4096
# Number of output sequences to return for the given prompt.
n: 1
# Float that controls the randomness of the sampling. Lower values make the
# model more deterministic, while higher values make the model more random. Zero
# means greedy sampling.
temperature: 0.01
# Random seed to use for the generation to ensure reproducibility.
seed: 42