Changed image size

app.py

@@ -14,7 +14,8 @@ Welcome to our Huggingface space, where you can explore the capabilities of TURN
 - **Powerful Architecture:** TURNA contains 1.1B parameters, and was pre-trained with an encoder-decoder architecture following the UL2 framework on 43B tokens from various domains.
 - **Diverse Training Data:** Our model is trained on a varied dataset of 43 billion tokens, covering a wide array of domains.
 - **Broad Applications:** TURNA is fine-tuned for a variety of generation and understanding tasks, including:
-	- Summarization
+    
+    - Summarization
 	- Paraphrasing
 	- News title generation
 	- Sentiment classification
@@ -136,8 +137,8 @@ def turna(input, max_new_tokens, length_penalty,
 
 
 with gr.Blocks(theme="abidlabs/Lime") as demo:
-    gr.Markdown("# TURNA 🐦")
-    gr.Image("images/turna-logo.png", scale=1)
+    gr.Markdown("# TURNA")
+    gr.Image("images/turna-logo.png", width=100)
 
     gr.Markdown(DESCRIPTION)