demo buildout 5

app.py

@@ -48,7 +48,7 @@ def infer(
         text: str,
         max_new_tokens: int
 ) -> str:
-    inputs = processor(text=text, images=resize_and_pad(image), return_tensors="pt").to(device)
+    inputs = processor(text=text, images=resize_and_pad(image, 448), return_tensors="pt").to(device)
     with torch.inference_mode():
         generated_ids = model.generate(
             **inputs,
@@ -129,8 +129,8 @@ with gr.Blocks(css="style.css") as demo:
             outputs=chat_outputs,
         )
 
-        examples = [["./diagnosis-1.jpg", "Transcribe the Arabic text."],
-                    ["./examples/sign.jpg", "Transcribe the Arabic text."]]
+        examples = [["./diagnosis-1.png", "Transcribe the Arabic text."],
+                    ["./sign.png", "Transcribe the Arabic text."]]
         gr.Markdown("")
 
         gr.Examples(