test

app.py

@@ -1,5 +1,24 @@
 # Load model directly
-from transformers import AutoProcessor, AutoModelForCausalLM
+#from transformers import AutoProcessor, AutoModelForCausalLM
 
-processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
-model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
+#processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
+#model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
+
+import gradio as gr
+from transformers import pipeline
+
+pipeline = pipeline(task="image-classification", model="llms-lab/LLaVA-NeXT-Video-32BQwen")
+
+def predict(input_img):
+    predictions = pipeline(input_img)
+    return input_img, {p["label"]: p["score"] for p in predictions} 
+
+gradio_app = gr.Interface(
+    predict,
+    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
+    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
+    title="Hot Dog? Or Not?",
+)
+
+if __name__ == "__main__":
+    gradio_app.launch()