Update README

README.md

@@ -8,9 +8,9 @@ This model is a fine-tuned version of [StableToolBench-MirrorAPI](https://huggin
 
 ### Training and evaluation data
 
-The training data is [`train_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/train/train_cache.json).
+The training data is [`train_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI-Training/blob/main/train_cache.json).
 
-The testing data is [`test_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/test/test_cache.json).
+The testing data is [`test_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI-Bench/blob/main/test_cache.json).
 
 # Getting Started
 
@@ -23,7 +23,7 @@ Please refer to [LLaMA-Factory/README.md](https://github.com/hiyouga/LLaMA-Facto
 ### Data Preparation
 
 As we use custom datasets, please make sure to add a dataset description in `dataset_info.json` and specify `dataset: dataset_name` before using it.
-For instance of adding [`test_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/test/test_cache.json):
+For instance of adding [`test_cache.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI-Bench/blob/main/test_cache.json):
 ```
 {
 ...