Update README.md

README.md

@@ -25,6 +25,8 @@ We study how to reduce bias in CLIP-style models by combining:
 - **Large-scale WebDataset shards** of synthetic / hybrid image–text data.
 - **Eval tools and benchmarks** for analysing bias and fairness in CLIP-like models.
 
+[![GitHub – evaluation tools](https://img.shields.io/badge/GitHub-Evaluation%20Tools-black?logo=github)](https://github.com/lluisgomez/SynthFairCLIP/tree/main/evals)
+
 If you use our resources, please consider citing the SynthFairCLIP project.
 
 ---