Update README.md (#1)

- Update README.md (f6e4855fcb61b1f04a88b87f614f2aa2df116b05)


Co-authored-by: Sayak Paul <sayakpaul@users.noreply.huggingface.co>

README.md

@@ -1,5 +1,5 @@
 ---
-title: Segformer Tf Transformers
+title: SegFormer (ADE20k) in TensorFlow
 emoji: 🏃
 colorFrom: indigo
 colorTo: gray
@@ -10,4 +10,8 @@ pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This space hosts the [SegFormer model](https://arxiv.org/abs/2105.15203) in TensorFlow. This model was fine-tuned on the [ADE20k dataset](http://groups.csail.mit.edu/vision/datasets/ADE20K/). To know more about the checkpoint used in this space, refer to the model card
+[here](https://huggingface.co/nvidia/segformer-b5-finetuned-ade-640-640).
+
+Please note that since the model was fine-tuned on the ADE20k dataset, the model is expected to provide best results for images
+belonging to scene categories. For an overview of the dataset, refer to its [homepage](http://groups.csail.mit.edu/vision/datasets/ADE20K/).