I tried to test a custom model by using the serverless api on vs code but I keep receiving this error ‘Status Code: 503
Response Text: {“error”:”Model merve/gemma-7b-it-8bit is currently loading”,”estimated_time”:373.2806091308594}
I tried to increase the wait time and retry times but it just loops and nothing changes, model still not loading, what am I doing wrong?
New contributor
Ines Belkahla is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.