fix: add link to model card

dashboard_featurefinder.py

@@ -68,8 +68,9 @@ def app():
     st.markdown("""
         The CLIP model from OpenAI is trained in a self-supervised manner using 
         contrastive learning to project images and caption text onto a common 
-        embedding space. We have fine-tuned the model using the RSICD dataset
-        (10k images and ~50k captions from the remote sensing domain).
+        embedding space. We have fine-tuned the model (see [Model card](https://huggingface.co/flax-community/clip-rsicd-v2)) 
+        using the RSICD dataset (10k images and ~50k captions from the remote 
+        sensing domain). 
         
         This demo shows the ability of the model to find specific features
         (specified as text queries) in the image. As an example, say you wish to

dashboard_image2image.py

@@ -48,8 +48,9 @@ def app():
     st.markdown("""
         The CLIP model from OpenAI is trained in a self-supervised manner using 
         contrastive learning to project images and caption text onto a common 
-        embedding space. We have fine-tuned the model using the RSICD dataset
-        (10k images and ~50k captions from the remote sensing domain).
+        embedding space. We have fine-tuned the model (see [Model card](https://huggingface.co/flax-community/clip-rsicd-v2)) 
+        using the RSICD dataset (10k images and ~50k captions from the remote 
+        sensing domain). 
         
         This demo shows the image to image retrieval capabilities of this model, i.e., 
         given an image file name as a query, we use our fine-tuned CLIP model 

dashboard_text2image.py

@@ -28,8 +28,9 @@ def app():
     st.markdown("""
         The CLIP model from OpenAI is trained in a self-supervised manner using 
         contrastive learning to project images and caption text onto a common 
-        embedding space. We have fine-tuned the model using the RSICD dataset
-        (10k images and ~50k captions from the remote sensing domain).
+        embedding space. We have fine-tuned the model (see [Model card](https://huggingface.co/flax-community/clip-rsicd-v2)) 
+        using the RSICD dataset (10k images and ~50k captions from the remote 
+        sensing domain). 
         
         This demo shows the image to text retrieval capabilities of this model, i.e., 
         given a text query, we use our fine-tuned CLIP model to project the text query