frozenleaves/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-20 12:54:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

1. add custom eval dataset support

Browse Source 
2. merge load dataset and split dataset function


Former-commit-id: 963d97ba07e7efa3a4544c4d077283d9e112b3ad
This commit is contained in:
codingma
2024-07-05 15:52:10 +08:00
parent 9a1a5f9778
commit 5f2bd04799
15 changed files with 93 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
data/README.md
View File

@ -12,7 +12,8 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
"ranking": "whether the dataset is a preference dataset or not. (default: False)",
"subset": "the name of the subset. (optional, default: None)",
"folder": "the name of the folder of the dataset repository on the Hugging Face hub. (optional, default: None)",
"num_samples": "the number of samples in the dataset used for training. (optional, default: None)",
"num_samples": "the number of samples in the dataset used for training. (optional, default: None)",
"split": "which dataset split to use for training and evaluation (optional, default: train)",
"columns (optional)": {
"prompt": "the column name in the dataset containing the prompts. (default: instruction)",
"query": "the column name in the dataset containing the queries. (default: input)",

1
data/README_zh.md
View File

@ -13,6 +13,7 @@
"subset": "数据集子集的名称（可选，默认：None）",
"folder": "Hugging Face 仓库的文件夹名称（可选，默认：None）",
"num_samples": "该数据集中用于训练的样本数量。（可选，默认：None）",
"split": "数据集中的要使用的训练测试集切分（可选，默认：train）",
"columns（可选）": {
"prompt": "数据集代表提示词的表头名称（默认：instruction）",
"query": "数据集代表请求的表头名称（默认：input）",