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

Merge branch 'main' into add_dataset_sample_num

Browse Source 
Former-commit-id: 26300127c45f24e63b91f1b0cc73e46c3a936a91
This commit is contained in:
seanzhang-zhichen
2024-05-24 15:57:47 +08:00
committed by GitHub
parent de9f1583c2 bf59383783
commit a3b52fd380
27 changed files with 756 additions and 513 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
data/README_zh.md
View File

@ -7,7 +7,7 @@
"hf_hub_url": "Hugging Face 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
"ms_hub_url": "ModelScope 的数据集仓库地址（若指定，则忽略 script_url 和 file_name）",
"script_url": "包含数据加载脚本的本地文件夹名称（若指定，则忽略 file_name）",
"file_name": "该目录下数据集文件的名称（若上述参数未指定，则此项必需）",
"file_name": "该目录下数据集文件夹或文件的名称（若上述参数未指定，则此项必需）",
"formatting": "数据集格式（可选，默认：alpaca，可以为 alpaca 或 sharegpt）",
"ranking": "是否为偏好数据集（可选，默认：False）",
"subset": "数据集子集的名称（可选，默认：None）",

3
data/hh_rlhf_en/hh_rlhf_en.py
View File

@ -34,7 +34,8 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
features = datasets.Features(
{
"instruction": datasets.Value("string"),
"output": datasets.Sequence(datasets.Value("string")),
"chosen": datasets.Value("string"),
"rejected": datasets.Value("string"),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string"))),
}
)