p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
hoshi-hiyouga 2024-07-14 21:27:04 +08:00 committed by GitHub
parent 76f3bbcfc0
commit 9d64507bd5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
data/README.md
View File

@ -11,9 +11,9 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
"formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})", "formatting": "the format of the dataset. (optional, default: alpaca, can be chosen from {alpaca, sharegpt})",
"ranking": "whether the dataset is a preference dataset or not. (default: False)", "ranking": "whether the dataset is a preference dataset or not. (default: False)",
"subset": "the name of the subset. (optional, default: None)", "subset": "the name of the subset. (optional, default: None)",
"split": "the name of dataset split to be used. (optional, default: train)",
"folder": "the name of the folder of the dataset repository on the Hugging Face hub. (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 to be used. (optional, default: None)",
"split": "which dataset split to use for training and evaluation (optional, default: train)",
"columns (optional)": { "columns (optional)": {
"prompt": "the column name in the dataset containing the prompts. (default: instruction)", "prompt": "the column name in the dataset containing the prompts. (default: instruction)",
"query": "the column name in the dataset containing the queries. (default: input)", "query": "the column name in the dataset containing the queries. (default: input)",