Questions about Critic model
leejaehoon1830 opened this issue · 2 comments
leejaehoon1830 commented
I am curious whether you only used llama2 13b to create data when generating your generation model's training data, or if you also used llama2 7b to generate generation model's training data.
notoookay commented
Hi, If I'm correct, the authors used GPT-4 model to get the training data, check paper for more specific details.
leejaehoon1830 commented
I know the dataset used for training the critic model in GPT-4, but I want to know about the dataset used for the generation model.