update readme

README.md

@@ -18,7 +18,7 @@ To address these limitations, we present EXAONE Path 2.0, a pathology foundation
 Using only 35k WSIs for training, EXAONE Path 2.0 achieves state-of-the-art average performance across 10 biomarker prediction tasks, demonstrating remarkable data efficiency. 
 
 ## Quickstart
-Load EXAONE Path and run inference on tile-level images.
+Load EXAONE Path 2.0 and extract features.
 
 ### 1. Prerequisites ###
 - NVIDIA GPU with 24GB+ VRAM
@@ -30,7 +30,7 @@ Note: This implementation requires NVIDIA GPU and drivers. The provided environm
 ```bash
 git clone https://github.com/LG-AI-EXAONE/EXAONE-Path-2.0.git
 cd EXAONE-Path-2.0
-pip install -r 
+pip install -r requirements.txt
 ```
 
 ### 3. Load the model & Inference
@@ -74,8 +74,8 @@ If you find EXAONE Path 2.0 useful, please cite it using this BibTeX:
   author={Yun, Juseung and Hu, Yi and Kim, Jinhyung and Jang, Jongseong and Lee, Soonyoung},
   journal={arXiv preprint arXiv:2408.00380},
   year={2024}
-} -->
-```
+}
+``` -->
 
 ## Contact
 LG AI Research Technical Support: <a href="mailto:[email protected]">[email protected]</a>