update app

app.py

@@ -2,6 +2,9 @@ from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+import os
+import uvicorn
+
 
 app = FastAPI()
 
@@ -11,7 +14,8 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     torch_dtype=torch.float16,
-    device_map="auto"
+    device_map="auto",
+    trust_remote_code=True,
 )
 
 # Request schema
@@ -46,3 +50,7 @@ def chat(req: ChatRequest):
 @app.get("/")
 def root():
     return {"message": "Qwen FastAPI running 🚀"}
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 7860))
+    uvicorn.run("app:app", host="0.0.0.0", port=port)