Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+from transformers import AutoModel, AutoTokenizer, AutoFeatureExtractor
+from PIL import Image
+
+# Load Deepseek-vl2-small model and tokenizer
+model_name = "Deepseek-vl2-small"  # Replace with actual model name if available on HF
+model = AutoModel.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+
+# Define inference function
+def process_image_text(image, text):
+    # Process inputs
+    image_input = feature_extractor(images=image, return_tensors="pt")
+    text_input = tokenizer(text, return_tensors="pt")
+
+    # Get model output
+    outputs = model(**text_input, **image_input)
+
+    # Process output (modify based on your model’s task)
+    return "Model processed the inputs successfully!"
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=process_image_text,
+    inputs=[gr.Image(type="pil"), gr.Textbox()],
+    outputs="text",
+    title="Deepseek-vl2-small Demo"
+)
+
+# Launch app
+interface.launch()