mirror of
https://github.com/wassname/evil_MoE.git
synced 2026-07-29 11:20:10 +08:00
transformers warns when generation_config is passed alongside generation kwargs like num_return_sequences. Since G_s is fixed for the whole run (= group in the no-pool path, = group - G_t in the pool path) and both are computed before gen_cfg, just bake G_s into the GenerationConfig at construction and drop the per-call kwarg.