423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-24 06:42:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #1909

Browse Source 
Former-commit-id: c6abbbfe90dcb0e832f73f0c611fc32eaa7ea78d
This commit is contained in:
hiyouga 2023-12-20 16:11:07 +08:00
parent a862ce636f
commit 633624dc3c
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/llmtuner/data/preprocess.py
View File

@ -44,6 +44,13 @@ def preprocess_dataset(
) -> Union["Dataset", "IterableDataset"]:
template = get_template_and_fix_tokenizer(data_args.template, tokenizer)
if data_args.cache_path is not None and os.path.exists(data_args.cache_path):
logger.warning("Loading dataset from disk will ignore other data arguments.")
dataset = load_from_disk(data_args.cache_path)
if data_args.streaming:
dataset = dataset.to_iterable_dataset()
return dataset
if data_args.train_on_prompt and template.efficient_eos:
raise ValueError("Current template does not support `train_on_prompt`.")
@ -240,10 +247,6 @@ def preprocess_dataset(
preprocess_func = preprocess_unsupervised_dataset
print_function = print_unsupervised_dataset_example
if data_args.cache_path is not None and os.path.exists(data_args.cache_path):
logger.warning("Loading dataset from disk will ignore other data arguments.")
return load_from_disk(data_args.cache_path)
with training_args.main_process_first(desc="dataset map pre-processing"):
column_names = list(next(iter(dataset)).keys())
kwargs = {}