Create app.py

app.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI
+from transformers import pipeline
+import torch
+from pydantic import BaseModel
+
+app = FastAPI()
+
+# Disable xformers if needed
+torch.backends.cuda.enable_flash_sdp(False)
+torch.backends.cuda.enable_mem_efficient_sdp(False)
+
+# Load model
+model = pipeline(
+    "text-classification",
+    model="win2win/3-epochs-classifier-ver2",
+    device="cuda" if torch.cuda.is_available() else "cpu"
+)
+
+class Request(BaseModel):
+    text: str
+
+@app.post("/predict")
+async def predict(request: Request):
+    return model(request.text)
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)