chore: Update app.py with improved Gradio interface for Sudoku Solver

app.py

@@ -1,15 +1,19 @@
 import gradio as gr
+import torch
+from PIL import Image
 from transformers import AutoModel, AutoTokenizer
 
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
 # Load the model
-model = AutoModel.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True)
+model = AutoModel.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True, torch_dtype=torch.float16)
+model = model.to(device=device)
 
 # Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained("openbmb/MiniCPM-Llama3-V-2_5", trust_remote_code=True)
 
 model.eval()
 
-
 # Define the Gradio components
 image = gr.Image(type="pil", label="Image")
 question = gr.Textbox(value="Using the standard 9x9 sudoku format, solve the sudoku puzzle in the image correctly.", label="Question")
@@ -20,17 +24,19 @@ description = "Sudoku Solver using MiniCPM-Llama3-V-2_5"
 
 # Define the function for solving Sudoku
 def solve_sudoku(image, question):
+    # Convert image to RGB format if not already in RGB
+    image = image.convert("RGB") if image.mode != 'RGB' else image
     msgs = [{"role": "user", "content": question}]
     res = model.chat(
         image=image,
         msgs=msgs,
         tokenizer=tokenizer,
-        sampling=True,
+        sampling=False,
         temperature=0.7,
-        stream=True,
+        stream=False,  # Enable streaming
         system_prompt="You are an expert in solving sudoku puzzles. Please solve the sudoku puzzle in the image correctly.",
     )
-    return res
+    return "".join(res)
 
 # Create the Gradio interface
 demo = gr.Interface(

requirements.txt

@@ -1,2 +1,5 @@
-transformers
-torch
+Pillow==10.1.0
+torch==2.1.2
+torchvision==0.16.2
+transformers==4.40.0
+sentencepiece==0.1.99