mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
ff3b741045
* feat: adding multimodal (only image for now) support in trtllm-bench Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * fix: add in load_dataset() calls to maintain the v2.19.2 behavior Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * re-adding prompt_token_ids and using that for prompt_len Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * updating the datasets version in examples as well Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * api changes are not needed Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * moving datasets requirement and removing a missed api change Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * addressing review comments Signed-off-by: Rakib Hasan <rhasan@nvidia.com> * refactoring the quickstart example Signed-off-by: Rakib Hasan <rhasan@nvidia.com> --------- Signed-off-by: Rakib Hasan <rhasan@nvidia.com>
40 lines
1.5 KiB
Python
40 lines
1.5 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2022-2024 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.
|
|
|
|
DATASET = "Magpie-Align/Magpie-Pro-MT-300K-v0.1"
|
|
|
|
|
|
def create_trtllm_magpie_calibration_dataset(output_dir: str,
|
|
calib_size: int = 512) -> None:
|
|
from datasets import load_dataset
|
|
|
|
dataset = load_dataset(DATASET, split="train", trust_remote_code=True)
|
|
|
|
def transform(conversation):
|
|
value = '\n'.join(turn['value']
|
|
for turn in conversation['conversations'])
|
|
return {"text": value}
|
|
|
|
dataset = dataset.select(range(calib_size)).map(
|
|
transform, remove_columns=dataset.column_names)
|
|
# https://github.com/huggingface/datasets/issues/6703#issuecomment-1974766332
|
|
dataset.to_parquet(output_dir + "/data.parquet")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import sys
|
|
output_dir = sys.argv[1]
|
|
create_trtllm_magpie_calibration_dataset(output_dir)
|