Update README.md

README.md

@@ -69,14 +69,13 @@ The best in MantisScore series is in bold and the best in baselines is underline
 "-" means the answer of MLLM is meaningless or in wrong format.
 
 ## Usage
-### Installation
-```bash
-pip install git+https://github.com/TIGER-AI-Lab/MantisScore.git
+```
+git clone https://github.com/TIGER-AI-Lab/MantisScore.git
 ```
 
 ### Inference
-```shell
-cd examples
+```
+cd MantisScore/examples
 ```
 
 ```python
@@ -129,7 +128,7 @@ all the frames of video are as follows:
 """
 
 model_name="TIGER-Lab/MantisScore-anno-only"
-video_path="examples/video1.mp4"
+video_path="video1.mp4"
 video_prompt="Near the Elephant Gate village, they approach the haunted house at night. Rajiv feels anxious, but Bhavesh encourages him. As they reach the house, a mysterious sound in the air adds to the suspense."
 
 processor = AutoProcessor.from_pretrained(model_name,torch_dtype=torch.bfloat16)
@@ -180,9 +179,9 @@ print(aspect_scores)
 ```
 
 ### Training
-see [MantisScore/training](https://github.com/TIGER-AI-Lab/MantisScore/training) for details
+see [MantisScore/training](https://github.com/TIGER-AI-Lab/MantisScore/tree/main/training) for details
 
 ### Evaluation
-see [MantisScore/benchmark]((https://github.com/TIGER-AI-Lab/MantisScore/benchmark)) for details
+see [MantisScore/benchmark](https://github.com/TIGER-AI-Lab/MantisScore/tree/main/benchmark) for details
 
 ## Citation