base_model/generation_config.json

{
  "do_sample": true,
  "repetition_penalty": 1.05,
  "temperature": 0.9,
  "top_p": 1.0,
  "top_k": 50,
  "subtalker_dosample": true,
  "subtalker_temperature": 0.9,
  "subtalker_top_p": 1.0,
  "subtalker_top_k": 50,
  "max_new_tokens": 8192
}