Update README.md

README.md

@@ -14,7 +14,7 @@ datasets:
 
 ### Model Summary
 
-CLIP_TROHN-Text is a model presented in the [BiVLC](https://github.com/IMirandaM/BiVLC) paper for experimentation. It has been fine-tuned with OpenCLIP framework using as basis the CLIP ViT-B-32 model pre-trained by 'openai'. Hyperparameters:
+CLIP_TROHN-Text is a model presented in the [BiVLC](https://github.com/IMirandaM/BiVLC) paper for experimentation. It has been fine-tuned with OpenCLIP framework using as basis the CLIP ViT-B-32 model pre-trained by 'openai'. The idea behind this fine-tuning is to improve the compositional understanding of the model by adding negative captions. The negatives present small compositional changes. Hyperparameters:
 
 * Learning rate: 1e-6.
 * Scheduler: Cosine scheduler with 50 warmup steps.