423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 03:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

update get template

Browse Source
This commit is contained in:
hiyouga
2024-09-04 22:36:20 +08:00
parent 8f441c2b3a
commit dabad5570b
17 changed files with 57 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
scripts/cal_lr.py
View File

@@ -25,7 +25,7 @@ from torch.utils.data import DataLoader
from tqdm import tqdm
from transformers import DataCollatorForLanguageModeling, DataCollatorForSeq2Seq
from llamafactory.data import get_dataset
from llamafactory.data import get_dataset, get_template_and_fix_tokenizer
from llamafactory.extras.constants import IGNORE_INDEX
from llamafactory.hparams import get_train_args
from llamafactory.model import load_tokenizer
@@ -66,7 +66,8 @@ def calculate_lr(
)
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
trainset = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)["train_dataset"]
template = get_template_and_fix_tokenizer(tokenizer, data_args)
trainset = get_dataset(template, model_args, data_args, training_args, stage, **tokenizer_module)["train_dataset"]
if stage == "pt":
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
elif stage == "sft":