423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-24 23:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #678 from hiyouga/feature-txt_preview

Browse Source 
add text format dataset preview in webui

Former-commit-id: 01dfba85b4dadc6d15460121bdbd2f9831e39f18
This commit is contained in:
codingma 2023-08-28 16:03:02 +08:00 committed by GitHub
commit b094b3edb8
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/llmtuner/webui/utils.py
View File

@ -6,6 +6,7 @@ import matplotlib.pyplot as plt
from typing import TYPE_CHECKING, Any, Dict, Generator, List, Tuple
from datetime import datetime
from llmtuner.dsets.utils import EXT2TYPE
from llmtuner.extras.ploting import smooth
from llmtuner.tuner import export_model
from llmtuner.webui.common import get_model_path, get_save_dir, DATA_CONFIG
@ -50,8 +51,15 @@ def get_preview(dataset_dir: str, dataset: list) -> Tuple[int, list, Dict[str, A
with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
dataset_info = json.load(f)
data_file = dataset_info[dataset[0]]["file_name"]
with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
data = json.load(f)
data = []
data_format = EXT2TYPE.get(data_file.split(".")[-1], None)
if data_format == "text":
with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
for line in f:
data.append(line.strip())
elif data_format == "json":
with open(os.path.join(dataset_dir, data_file), "r", encoding="utf-8") as f:
data = json.load(f)
return len(data), data[:2], gr.update(visible=True)