Update app.py

app.py

@@ -66,43 +66,21 @@ def run(history, text, image, audio_upload, audio_mic):
 
 with gr.Blocks(theme='upsatwal/mlsc_tiet') as demo:
 
-    gr.Text(" " * 50 + "MulitModal Phi2 Model Pretraining and Finetuning from Scratch")
+    with gr.Row() as title_row:
+        with gr.Column():
+            # Create an empty column on the left for spacing
+            pass
     
-    # with gr.Row() as title_row:
-    #     with gr.Column():
-    #         # Create an empty column on the left for spacing
-    #         pass
-    
-    #     with gr.Column():
-    #         # Add Markdown with centered text
-    #         gr.Markdown("## MulitModal Phi2 Model Pretraining and Finetuning from Scratch")
-    #         gr.Markdown("This is a multimodal implementation of [Phi2](https://huggingface.co/microsoft/phi-2) model. Please find the source code and training details [here](https://github.com/RaviNaik/ERA-CAPSTONE/MultiModalPhi2).")
+        with gr.Column():
+            # Add Markdown with centered text
+            gr.Markdown("## MulitModal Phi2 Model Pretraining and Finetuning from Scratch")
+            gr.Markdown("This is a multimodal implementation of [Phi2](https://huggingface.co/microsoft/phi-2) model. Please find the source code and training details [here](https://github.com/RaviNaik/ERA-CAPSTONE/MultiModalPhi2).")
         
     
-    #     # with gr.Column():
-    #     #     # Create an empty column on the right for spacing
-    #     #     pass
-
-    gr.Markdown(
-        """This is a multimodal implementation of [Phi2](https://huggingface.co/microsoft/phi-2) model. Please find the source code and training details [here](https://github.com/RaviNaik/ERA-CAPSTONE/MultiModalPhi2).
-        
-        ### Details:
-        1. LLM Backbone: [Phi2](https://huggingface.co/microsoft/phi-2)
-        2. Vision Tower: [clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336)
-        3. Audio Model: [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) 
-        4. Pretraining Dataset: [LAION-CC-SBU dataset with BLIP captions(200k samples)](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain)
-        5. Finetuning Dataset: [Instruct 150k dataset based on COCO](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K)
-        6. Finetuned Model: [GunaKoppula/Llava-Phi2](https://huggingface.co/GunaKoppula/Llava-Phi2)
-        """
-    )
+        # with gr.Column():
+        #     # Create an empty column on the right for spacing
+        #     pass
 
-    # with gr.Row(scale=8):
-    #     with gr.Box():
-    #         with gr.Row():
-    #             chatbot = gr.Chatbot(
-    #                 avatar_images=("🧑", "🤖"),
-    #                 height=550,
-    #             )
 
     with gr.Row():
         chatbot = gr.Chatbot(