From 9d64507bd5d47f096e81c90bfb347690afaaec2b Mon Sep 17 00:00:00 2001 From: hoshi-hiyouga Date: Sun, 14 Jul 2024 21:27:04 +0800 Subject: [PATCH] Update README.md --- data/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/data/README.md b/data/README.md index 0f14bef8..5a34bcbe 100644 --- a/data/README.md +++ b/data/README.md @@ -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})", "ranking": "whether the dataset is a preference dataset or not. (default: False)", "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)", - "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)", + "num_samples": "the number of samples in the dataset to be used. (optional, default: None)", "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)",