Update app.py

app.py

@@ -73,7 +73,7 @@ class ModelManager:
                 llama = Llama.load(temp_filename)
                 end_time = time.time()
                 load_duration = end_time - start_time
-                if load_duration > 0.5:
+                if load_duration > 0:
                     print(f"Modelo {model_config['name']} tardó {load_duration:.2f} segundos en cargar, dividiendo automáticamente")
                     await self.handle_large_model(temp_filename, model_config)
                 else:
@@ -164,7 +164,7 @@ async def generate(request: Request):
         raise HTTPException(status_code=500, detail=str(e))
 
 def start_uvicorn():
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=7860)
 
 if __name__ == "__main__":
     asyncio.run(start_uvicorn())