I’ve been trying to access the inference API for the model google/flan-ul2 for the past 2 days, but I keep getting an error 504: response time-out. The model is not loading (the web-UI inference doesn’t work either). The problem persists even after using my access token (pro). Any suggestions?
Not sure if for the same reasons, but I also couldn’t get endpoints to run on flan-t5-xxl or fan-ul2 on GPU [large] instances. And xlarge wasn’t accessible to me.