In this lesson, in the parameter_values creation step, there is no paramater defined for Reward Model, only the Base Model ( "large_model_reference": "llama-2-7b") is passed. Where is reward model defined? Appreciate clarifications.
In this lesson, in the parameter_values creation step, there is no paramater defined for Reward Model, only the Base Model ( "large_model_reference": "llama-2-7b") is passed. Where is reward model defined? Appreciate clarifications.