mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-08 09:03:20 +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>
43 lines
1.6 KiB
Python
43 lines
1.6 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 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.
|
|
|
|
import os
|
|
|
|
import pytest
|
|
from _test_utils.examples.run_command import MODELOPT_ROOT, run_example_command
|
|
|
|
|
|
@pytest.fixture(scope="session", autouse=True)
|
|
def tiny_daring_anteater_path(tmp_path_factory):
|
|
dataset_path = (
|
|
MODELOPT_ROOT / "examples/speculative_decoding/input_conversations/daring-anteater.jsonl"
|
|
)
|
|
if not os.path.exists(dataset_path):
|
|
try:
|
|
run_example_command(
|
|
["python", "prepare_input_conversations/add_daring_anteater.py"],
|
|
"speculative_decoding",
|
|
)
|
|
except Exception as e:
|
|
# Ignore rate-limiting errors
|
|
pytest.skip(f"Failed to prepare dataset: {e}")
|
|
output_path = tmp_path_factory.mktemp("daring_anteater") / "train.jsonl"
|
|
with open(dataset_path) as src, open(output_path, "w") as dst:
|
|
for i, line in enumerate(src):
|
|
if i >= 128:
|
|
break
|
|
dst.write(line)
|
|
return output_path
|