423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

support streaming data, fix #284 #274 #268

Browse Source
This commit is contained in:
hiyouga
2023-07-31 23:33:00 +08:00
parent 513e1f1ec9
commit 0411a4b3e1
28 changed files with 478 additions and 344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src/llmtuner/tuner/pt/workflow.py
View File

@@ -1,24 +1,27 @@
# Inspired by: https://github.com/huggingface/transformers/blob/v4.29.2/examples/pytorch/language-modeling/run_clm.py
import math
from typing import Optional, List
from transformers import Seq2SeqTrainingArguments, DataCollatorForSeq2Seq, TrainerCallback
from typing import TYPE_CHECKING, Optional, List
from transformers import DataCollatorForSeq2Seq
from llmtuner.dsets import get_dataset, preprocess_dataset, split_dataset
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.constants import IGNORE_INDEX
from llmtuner.extras.ploting import plot_loss
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
from llmtuner.tuner.core import load_model_and_tokenizer
from llmtuner.tuner.core.trainer import PeftTrainer
if TYPE_CHECKING:
from transformers import Seq2SeqTrainingArguments, TrainerCallback
from llmtuner.hparams import ModelArguments, DataArguments, FinetuningArguments
def run_pt(
model_args: ModelArguments,
data_args: DataArguments,
training_args: Seq2SeqTrainingArguments,
finetuning_args: FinetuningArguments,
callbacks: Optional[List[TrainerCallback]] = [LogCallback()]
model_args: "ModelArguments",
data_args: "DataArguments",
training_args: "Seq2SeqTrainingArguments",
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = [LogCallback()]
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, stage="pt")