diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 7420a3176d930..2a83d66279b79 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -17965,6 +17965,8 @@ struct llm_build_plamo2 : public llm_graph_context_mamba { cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1); cb(cur, "result_norm", -1); + res->t_embd = cur; + // lm_head cur = build_lora_mm(model.output, cur); cb(cur, "result_output", -1);