Deployed model giving content type error

Question

I have deployed a pre trained hugging face model using jumpstart and it gives this error when i am hitting it in test interference.
Error invoking endpoint: Received client error (400) from primary with message "{ "code": 400, "type": "InternalServerException", "message": "{\"error\": \"unsupported content type application/json\"}" }

Answer

While I am not sure of the exact model you are using, I suggest taking a look at the example notebook of the respective JumpStart model and use the same input format and content type the example uses when making prediction (.predict() / InvokeEndpoint ).

Deployed model giving content type error

Conteúdo relevante