Update app.py

app.py

@@ -21,7 +21,7 @@ model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 print("------------------------- 4 -------------------------\n")
 
 
-def predict(image,max_length=64, num_beams=4):
+def predict(image, max_length=64, num_beams=4):
   image = image.convert('RGB')
   image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
   clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
@@ -49,24 +49,28 @@ title = "Image to Text ViT with LORA"
 # interface.launch(debug=True)
 
 with gr.Blocks() as demo:
+    
 
     gr.HTML(
         """
         <div style="text-align: center; max-width: 1200px; margin: 20px auto;">
         <h1 style="font-weight: 900; font-size: 3rem; margin: 0rem">
-            ViT Image-to-Text algorithms with LORA
+            ViT Image-to-Text with LORA
         </h1>   
         <h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 2rem; margin-bottom: 1.5rem">
         In the field of large language models, the challenge of fine-tuning has long perplexed researchers. Microsoft, however, has unveiled an innovative solution called <b>Low-Rank Adaptation (LoRA)</b>. With the emergence of behemoth models like GPT-3 boasting billions of parameters, the cost of fine-tuning them for specific tasks or domains has become exorbitant.
         LoRA offers a groundbreaking approach by freezing the weights of pre-trained models and introducing trainable layers known as <b>rank-decomposition matrices in each transformer block</b>. This ingenious technique significantly reduces the number of trainable parameters and minimizes GPU memory requirements, as gradients no longer need to be computed for the majority of model weights.        
         <br>
         <br>
-        You can find more info here: <a href="https://www.linkedin.com/pulse/fine-tuning-image-to-text-algorithms-with-lora-daniel-puente-viejo" target="_blank">Linkedin article</a>
+        You can find more info here: <a href="https://www.linkedin.com/pulse/fine-tuning-image-to-text-algorithms-with-lora-daniel-puente-viejo" target="_blank" style="text-decoration: underline;>Linkedin article</a>
         </h2>
         
         </div>
         """)
-    gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
-    gr.outputs.Textbox(type="text",label="Captions")   
+    with gr.Row():
+            with gr.Column(scale=1):
+                gr.inputs.Image(label="Upload any Image", type = 'pil', optional=True)
+            with gr.Column(scale=1):
+                gr.outputs.Textbox(type="text",label="Captions")   
 
 demo.launch(debug=True)