mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-10-31 07:43:00 +08:00
h-guo18
b8a4586702
## What does this PR do? **Type of change:** Refactor <!-- Use one of the following: Bug fix, new feature, new example, new tests, documentation. --> **Overview:** Jira ticket: https://jirasw.nvidia.com/browse/OMNIML-2955 Main changes : - Consolidate Eagle data loading with @ChenhanYu 's implementation of `transformers_dataset.py` - Refactor: baked the following logics from `example/main.py` to `modelopt/torch` for cleaner example entrance: - default config selecting and merging with custom config - tokenizer post-processor (chat template and pad_tok_id) - d2t loading - Implementation refactor: In HF workflow, reuse base modfel's input hidden states as input_embedding, instead of calculating from input_ids. This has two main benefits: - Easier VLM support, which has various embedding processing logics. - Training effieicy. - Deprecating eagle1 from the example. It is still available by setting custom config. - Other minor fixes and readme updates. ## Usage <!-- You can potentially add a usage example below. --> ```python # Add a code snippet demonstrating how to use this ``` ## Testing <!-- Mention how have you tested your change if applicable. --> Tested that training curves after changes (both online&offline) is identical with original branch: <img width="1073" height="634" alt="image" src="https://github.com/user-attachments/assets/abfd7bea-c82c-48a7-8181-68c5a9e4da8d" /> ## Before your PR is "*Ready for review*" <!-- If you haven't finished some of the above items you can still open `Draft` PR. --> - **Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)** and your commits are signed. - **Is this change backward compatible?**: Yes/No <!--- If No, explain why. --> - **Did you write any new necessary tests?**: Yes/No - **Did you add or update any necessary documentation?**: Yes/No - **Did you update [Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**: Yes/No <!--- Only for new features, API changes, critical bug fixes or bw breaking changes. --> ## Additional Information <!-- E.g. related issue. --> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Release Notes * **New Features** * Added draft vocabulary cache support for EAGLE model training, enabling runtime vocabulary customization via `--draft_vocab_cache` parameter * Introduced new data loading utilities with sharding, streaming, and tokenization support for large-scale training * Added optional `--log_steps` configuration to training launcher * **Documentation** * Updated EAGLE configuration guides with draft vocabulary cache setup instructions and examples * **Refactor** * Restructured data pipeline for offline training with improved dataset handling and batching * Updated command-line arguments across training scripts (`--input-data` replaces `--input-file`) <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
49 lines
1.6 KiB
Python
49 lines
1.6 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2023-2025 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.
|
|
|
|
"""Export a HF checkpoint (with ModelOpt state) for deployment."""
|
|
|
|
import argparse
|
|
|
|
import torch
|
|
|
|
import modelopt.torch.opt as mto
|
|
from modelopt.torch.export import export_hf_checkpoint
|
|
from modelopt.torch.speculative.utils import load_vlm_or_llm_with_kwargs
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(
|
|
description="Export a HF checkpoint (with ModelOpt state) for deployment."
|
|
)
|
|
parser.add_argument("--model_path", type=str, default="Path of the trained checkpoint.")
|
|
parser.add_argument(
|
|
"--export_path", type=str, default="Destination directory for exported files."
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
mto.enable_huggingface_checkpointing()
|
|
|
|
args = parse_args()
|
|
_, model = load_vlm_or_llm_with_kwargs(args.model_path, torch_dtype="auto")
|
|
model.eval()
|
|
with torch.inference_mode():
|
|
export_hf_checkpoint(
|
|
model,
|
|
export_dir=args.export_path,
|
|
)
|
|
print(f"Exported checkpoint to {args.export_path}")
|