diff --git a/examples/mistral/mixtral.yml b/examples/mistral/mixtral.yml index 15df88f96..11c842d4e 100644 --- a/examples/mistral/mixtral.yml +++ b/examples/mistral/mixtral.yml @@ -23,6 +23,9 @@ unfrozen_parameters: # - model.layers.3[0-9]+.block_sparse_moe.gate.* # - model.layers.3[0-9]+.block_sparse_moe.experts.* +model_config: + output_router_logits: true + adapter: qlora lora_model_dir: