Update README.md

README.md

@@ -12,7 +12,9 @@ tags:
 - EmoSet
 ---
 
-PreceptCLIP-Emotions is a model designed to predict the emotions that an image evokes in users. This is the official model from the paper ["Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks"](https://arxiv.org/abs/2503.13260). We apply LoRA adaptation on the CLIP visual encoder with an additional MLP head. Our model *achieves state-of-the-art results*.
+**PerceptCLIP-Emotions** is a model designed to predict the **emotions** that an image evokes in users. This is the official model from the paper:  
+📄 **["Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks"](https://arxiv.org/abs/2503.13260)**
+We apply **LoRA adaptation** on the **CLIP visual encoder** and add an **MLP head** for emotion classification. Our model achieves **state-of-the-art results**.
 
 ## Training Details
 
@@ -23,7 +25,8 @@ PreceptCLIP-Emotions is a model designed to predict the emotions that an image e
 - *Learning Rate*: 0.0001
 - *Batch Size*: 32
 
-## Requirements
+## Installation & Requirements
+You can set up the environment using environment.yml or manually install dependencies:
 - python=3.9.15
 - cudatoolkit=11.7
 - torchvision=0.14.0