Add app.py to deploy the model

app.py

@@ -0,0 +1,13 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained("HIT-TMG/bge-m3_RAG-conversational-IR")
+model = AutoModel.from_pretrained("HIT-TMG/bge-m3_RAG-conversational-IR")
+
+def predict(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = model(**inputs)
+    return outputs.last_hidden_state[0][0].tolist()
+
+iface = gr.Interface(fn=predict, inputs="text", outputs="text")
+iface.launch()