Update app.py

app.py

@@ -30,7 +30,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 # Load text-only model and tokenizer
-model_id = "prithivMLmods/FastThink-0.5B-Tiny"
+model_id = "prithivMLmods/Pocket-Llama-3.2-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -39,7 +39,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 model.eval()
 
-MODEL_ID = "prithivMLmods/Qwen2-VL-OCR-2B-Instruct" 
+MODEL_ID = "prithivMLmods/Callisto-OCR3-2B-Instruct" 
 processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
 model_m = Qwen2VLForConditionalGeneration.from_pretrained(
     MODEL_ID,
@@ -236,6 +236,10 @@ demo = gr.ChatInterface(
         gr.Slider(label="Top-k", minimum=1, maximum=1000, step=1, value=50),
         gr.Slider(label="Repetition penalty", minimum=1.0, maximum=2.0, step=0.05, value=1.2),
     ],
+    examples=[
+        ["Write the code that converts temperatures between celsius and fahrenheit"],
+        [{"text": "Create a short story based on the image.", "files": ["examples/1.jpg"]}],
+    ],
     cache_examples=False,
     type="messages",
     fill_height=True,