mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-04 20:52:59 +08:00
1fee69f874
* fix llamapro script * change year Former-commit-id: e2dc5b952aa22835d5220ba624f44676138b65ac
93 lines
3.2 KiB
Python
93 lines
3.2 KiB
Python
# Copyright 2025 the LlamaFactory team.
|
|
#
|
|
# 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.
|
|
|
|
from enum import Enum, unique
|
|
from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Set, TypedDict, Union
|
|
|
|
from datasets import DatasetDict, concatenate_datasets, interleave_datasets
|
|
|
|
from ..extras import logging
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
from datasets import Dataset, IterableDataset
|
|
|
|
from ..hparams import DataArguments
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
SLOTS = Sequence[Union[str, Set[str], Dict[str, str]]]
|
|
|
|
|
|
@unique
|
|
class Role(str, Enum):
|
|
USER = "user"
|
|
ASSISTANT = "assistant"
|
|
SYSTEM = "system"
|
|
FUNCTION = "function"
|
|
OBSERVATION = "observation"
|
|
|
|
|
|
class DatasetModule(TypedDict):
|
|
train_dataset: Optional[Union["Dataset", "IterableDataset"]]
|
|
eval_dataset: Optional[Union["Dataset", "IterableDataset"]]
|
|
|
|
|
|
def merge_dataset(
|
|
all_datasets: List[Union["Dataset", "IterableDataset"]], data_args: "DataArguments", seed: int
|
|
) -> Union["Dataset", "IterableDataset"]:
|
|
r"""
|
|
Merges multiple datasets to a unified dataset.
|
|
"""
|
|
if len(all_datasets) == 1:
|
|
return all_datasets[0]
|
|
elif data_args.mix_strategy == "concat":
|
|
if data_args.streaming:
|
|
logger.warning_rank0_once("The samples between different datasets will not be mixed in streaming mode.")
|
|
|
|
return concatenate_datasets(all_datasets)
|
|
elif data_args.mix_strategy.startswith("interleave"):
|
|
if not data_args.streaming:
|
|
logger.warning_rank0_once("We recommend using `mix_strategy=concat` in non-streaming mode.")
|
|
|
|
return interleave_datasets(
|
|
datasets=all_datasets,
|
|
probabilities=data_args.interleave_probs,
|
|
seed=seed,
|
|
stopping_strategy="first_exhausted" if data_args.mix_strategy.endswith("under") else "all_exhausted",
|
|
)
|
|
else:
|
|
raise ValueError(f"Unknown mixing strategy: {data_args.mix_strategy}.")
|
|
|
|
|
|
def split_dataset(
|
|
dataset: Union["Dataset", "IterableDataset"], data_args: "DataArguments", seed: int
|
|
) -> "DatasetDict":
|
|
r"""
|
|
Splits the dataset and returns a dataset dict containing train set and validation set.
|
|
|
|
Supports both map dataset and iterable dataset.
|
|
"""
|
|
if data_args.streaming:
|
|
dataset = dataset.shuffle(buffer_size=data_args.buffer_size, seed=seed)
|
|
val_set = dataset.take(int(data_args.val_size))
|
|
train_set = dataset.skip(int(data_args.val_size))
|
|
return DatasetDict({"train": train_set, "validation": val_set})
|
|
else:
|
|
val_size = int(data_args.val_size) if data_args.val_size > 1 else data_args.val_size
|
|
dataset = dataset.train_test_split(test_size=val_size, seed=seed)
|
|
return DatasetDict({"train": dataset["train"], "validation": dataset["test"]})
|