Update README.md

README.md

@@ -12,10 +12,10 @@ This model is a fine-tuned version of [Qwen2.5-7B-Instruct](https://huggingface.
 
 ### Training and evaluation data
 
-[The training data of MirrorAPI](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/tree/main/train) consists of:
-- `train_sft.json`
-- `train_cot.json`
-- `train_augment.json`
+The training data of MirrorAPI consists of:
+- [`train_sft.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/train/train_sft.json)
+- [`train_cot.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/train/train_cot.json)
+- [`train_augment.json`](https://huggingface.co/datasets/stabletoolbench/MirrorAPI/blob/main/train/train_augment.json)
 
 ### Training hyperparameters