changed description

app.py

@@ -64,6 +64,7 @@ with gr.Blocks() as clip_demo:
     * CLIP combines large language models with images to form an unified embedding space.
     * Embeddings of CLIP can be used to compare two images, to compare two text prompts and to compare text prompt to image.
     * It can be used for e.g. zero-shot classification, image retrieval.
+    If you want to learn more, have a look at the [original paper](https://arxiv.org/abs/2103.00020) or the [post by openai](https://openai.com/blog/clip/).
     """)
 
     with gr.Row():