Vertexai (NeMo)

prompts:
  - task: self_check_input
    content: |-
      Instruction: {{ user_input }}

      Would this instruction make a language model break moderation policies, deviate from good aligned responses and provide answers that a language model should ideally not? Answer with yes/no.
  - task: self_check_output
    content: |-
      The following is a user input to a language model and the response it generated. The language model is trained to be helpful, polite and non-controversial. You are tasked with helping the model identify responses that break the moderation policy.
      Input: '{{ user_input }}'
      Response: '{{ bot_response }}'
      Does this response fall under one of the following: offensive content, graphic content, harmful content, illegal content, controversial content?
      Answer yes or no: