upload

app.py

@@ -19,9 +19,7 @@ model.to("cuda:0")
 
 PLACEHOLDER = """
 <div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <img src="https://cdn-thumbnails.huggingface.co/social-thumbnails/models/microsoft/Phi-3-vision-128k-instruct.png" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55;  "> 
-   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">Microsoft's Phi3 Vision</h1>
-   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Phi-3-Vision is a 4.2B parameter multimodal model that brings together language and vision capabilities.</p>
+   <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">DifferentByte vision model</p>
 </div>
 """
 
@@ -44,10 +42,10 @@ def bot_streaming(message, history):
     try:
         if image is None:
             # Handle the case where image is None
-            raise gr.Error("You need to upload an image for Phi3-Vision to work. Close the error and try again with an Image.")
+            raise gr.Error("You need to upload an image for DifferentByte Vision to work. Close the error and try again with an Image.")
     except NameError:
         # Handle the case where 'image' is not defined at all
-        raise gr.Error("You need to upload an image for Phi3-Vision to work. Close the error and try again with an Image.")
+        raise gr.Error("You need to upload an image for Vision to work. Close the error and try again with an Image.")
 
     conversation = []
     flag=False
@@ -90,14 +88,14 @@ chat_input = gr.MultimodalTextbox(interactive=True, file_types=["image"], placeh
 with gr.Blocks(fill_height=True, ) as demo:
     gr.ChatInterface(
     fn=bot_streaming,
-    title="Phi3 Vision 128K Instruct",
+    title="DifferentByt",
     examples=[{"text": "Describe the image in details?", "files": ["./robo.jpg"]},
               {"text": "What does the chart display?", "files": ["./dataviz.png"]},
               {"text": "What is 3?", "files": ["./setofmark1.jpg"]},
               {"text": "Count the number of apples.", "files": ["./setofmark6.png"]},
               {"text": "I want to find a seat close to windows, where can I sit?", "files": ["./office1.jpg"]},
              ],
-    description="Try the [Phi3-Vision model](https://huggingface.co/microsoft/Phi-3-vision-128k-instruct) from Microsoft. Upload an image and start chatting about it, or simply try one of the examples below. If you won't upload an image, you will receive an error. This is not the official demo.",
+    description="Upload an image and start chatting.This is not the official demo.",
     stop_btn="Stop Generation",
     multimodal=True,
     textbox=chat_input,